Skip to content

Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.

docs: refresh project messaging and Lens website

Martin Vogeldd357a7c9718
diff --git a/README.md b/README.md
index ee1db98bb..74a2eaf71 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# codebase-memory-mcp: local MCP server for code search, lower token usage and visualization
+# codebase-memory-mcp: local code intelligence for developers and AI agents
[![GitHub Release](https://img.shields.io/github/v/release/DeusData/codebase-memory-mcp?style=flat&color=blue)](https://github.com/DeusData/codebase-memory-mcp/releases/latest)
[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
@@ -15,19 +15,13 @@
[![VirusTotal](https://img.shields.io/badge/VirusTotal-scanned_every_release-brightgreen?logo=virustotal)](https://github.com/DeusData/codebase-memory-mcp/releases/latest)
[![arXiv](https://img.shields.io/badge/arXiv-2603.27277-b31b1b?logo=arxiv)](https://arxiv.org/abs/2603.27277)
-**Search your code, follow call graphs, and explore software architecture in your browser.** codebase-memory-mcp is a local [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) server that gives Claude Code, Codex, and other coding agents a persistent code knowledge graph. It indexes functions, classes, imports, HTTP routes, and their relationships across [162 languages](#language-support). [Hybrid LSP](#hybrid-lsp) adds semantic type resolution for **Python, TypeScript, JavaScript, JSX/TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl**.
+**Understand your repository, from source code to the systems around it.** codebase-memory-mcp connects code, documentation, configuration, and infrastructure in a persistent local knowledge graph. Use it to find an unfamiliar feature, follow a call across services, trace a deployment back to its source, or assess which parts of a project a change could affect.
-**About 120× fewer tokens** in the project's reported five-query comparison: ~3,400 vs ~412,000 with file-by-file exploration. Published backend benchmarks also report **Linux kernel indexing in ~3 minutes** (28M lines of code) and **Cypher relationship queries under 1 ms** on an Apple M3 Pro. [Benchmark details](#performance).
+Give your coding agent structural context through [Model Context Protocol](https://modelcontextprotocol.io/) (MCP), query the graph from the CLI, or explore it yourself in **CBM Lens Beta**. Lens brings together an IDE-style source reader, architecture maps, the Galaxy graph, coverage diagnostics, architecture decisions, and optional local code chat.
-**CBM Lens Beta helps you understand unfamiliar code and stay in control as it grows.** Use it to get up to speed in a new codebase, tackle rescue engineering on an inherited project, or make sense of 50,000 lines of AI-generated code from a single day. Its IDE-style source reader, local code chat, 3D architecture map, and Galaxy graph let you see how the code fits together and follow dependencies and call paths back to the source. Use that context to review changes, investigate fragile areas, and keep code quality high. Architecture decisions stay alongside the project's index.
+The native C backend exposes **17 MCP tools**, parses [languages and file formats](#language-support) with vendored grammars, and adds [Hybrid LSP](#hybrid-lsp) type resolution for supported languages. The installer supports **45 automatic or conditional client integrations**, including client configuration, skills, agent profiles, and applicable hooks. Indexing and graph queries need no hosted service or API key.
-The native C backend exposes 17 MCP tools and supports 45 automatic or conditional client integrations. Indexing and graph queries need no hosted service or API key.
-
-> **CBM Lens Beta is new on `main`:** it arrived with [PR #2068](https://github.com/DeusData/codebase-memory-mcp/pull/2068) and is not part of the current v0.11.0 release, whose installer still ships the previous graph UI. To run the interface shown below now, [build from source](#build-from-source).
-
-[Quick start](#quick-start) · [Explore CBM Lens](#cbm-lens-beta-code-visualization-and-source-navigation) · [Chat with your codebase locally](#chat-with-your-codebase-locally) · [MCP tools](#mcp-tools) · [Build from source](#build-from-source)
-
-> **Research:** The [preprint](https://arxiv.org/abs/2603.27277) compares agents across 31 repositories, reporting **10× lower token use** and **2.1× fewer tool calls**, with answer-quality scores of 83% for CBM versus 92% for file-by-file exploration. These backend results are separate from the five-query comparison above and from CBM Lens.
+[Quick start](#quick-start) · [Capabilities](#features) · [Documentation](#documentation-connected-to-code) · [Infrastructure](#infrastructure-and-deployment) · [Smart CI](#smart-ci-and-test-impact) · [Explore CBM Lens](#cbm-lens-beta-code-visualization-and-source-navigation) · [Agent setup](#agent-setup-skills-profiles-and-hooks) · [MCP tools](#mcp-tools)
> **Local processing:** Source analysis and graph storage run on your machine. CBM Lens can optionally download a model for browser AI after you enable it; inference stays on the device. The installer writes agent configuration for the clients you select. See [Security](#security) for release verification and [SECURITY.md](SECURITY.md) for reporting issues.
@@ -62,23 +56,23 @@ These captures show CBM Lens Beta on 12–13 October 2026, using public source f
## Why codebase-memory-mcp
-- **Indexing performance**: Linux kernel (28M LOC, 75K files) in 3 minutes. RAM-first pipeline: LZ4 compression, in-memory SQLite, fused Aho-Corasick pattern matching. Memory released after indexing.
-- **Plug and play**: native executable plus authenticated release-owned assets for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (arm64/amd64). The native install needs no Docker, language runtime, or API keys. Download → `install` → restart agent → done.
-- **162 languages**: vendored tree-sitter grammars compiled into the binary. No separate parser installation.
-- **About 120× fewer tokens in the reported five-query comparison**: ~3,400 tokens vs ~412,000 via file-by-file search. See [Performance](#performance) for the scope and sources.
-- **45 supported automatic/conditional client surfaces**: `install` configures detected clients and safely activates conditional clients only when their documented platform, marker, or explicit existing config path is present. See [Multi-Agent Support](#multi-agent-support) for the complete matrix and manual/UI-only boundaries.
-- **CBM Lens Beta**: read source, chat about selected code with a local model, explore architecture and call graphs, inspect coverage gaps, and edit architecture decision records in your browser.
-- **Infrastructure-as-code indexing**: Dockerfiles, container images, docker compose, Kubernetes manifests, and Kustomize overlays indexed as graph nodes with cross-references. `Resource` nodes for K8s kinds and compose services, `Image` nodes joining the images that are built and run, `Module` nodes for Kustomize overlays with `IMPORTS` edges to referenced resources; a Service walks to the program its container runs.
-- **17 MCP tools**: search, trace, architecture, impact analysis, targeted index-coverage checks, Cypher queries, dead code detection, cross-service HTTP linking, ADR management, and more.
+- **Find the right code with context**: combine symbol, text, and semantic search with callers, dependencies, source snippets, and file outlines. Reduce repeated file exploration; see [Performance](#performance) for scoped measurements.
+- **Connect documentation to implementation**: index document sections, PDF text pages, architecture decisions, and supported references into code. Find the explanation alongside the symbol.
+- **Follow the system beyond source files**: trace supported relationships through Docker, Kubernetes, Helm, Kustomize, Terraform/OpenTofu, Terragrunt, Ansible, scripts, Make, and CI configuration.
+- **Understand a change before running it**: inspect affected symbols, compare indexed snapshots, and find related tests. [Experimental Smart CI](#smart-ci-and-test-impact) combines static relationships and per-test coverage for supported C/C++ test harnesses, falling back to broader runs when evidence is insufficient.
+- **Explore visually with CBM Lens Beta**: read source, follow call paths, inspect architecture and coverage gaps, manage architecture decisions, and ask a local model about selected code.
+- **Equip your coding agents**: `install` sets up supported client configuration, durable guidance, skills, Scout/Verify/Auditor profiles, and applicable context hooks. Support varies by client; see the [integration matrix](#multi-agent-support).
+- **Keep context local and reusable**: indexes persist between sessions, eligible active MCP sessions can keep them synchronized, and optional graph artifacts let a team share a baseline.
+- **Run a native tool on your machine**: standard releases include CBM Lens for macOS, Linux, and Windows. The native runtime needs no Docker or language runtime; parser grammars are included.
## Quick Start
-**Install the latest release** (macOS / Linux). For CBM Lens Beta shown above, [build from source](#build-from-source) until the next release.
+**Install the latest release** (macOS / Linux):
```bash
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash
```
-The released graph UI is included in the standard installer.
+The standard native release includes CBM Lens. Start it after installation with `codebase-memory-mcp daemon start --open --port=9749`. The [Nix packages](#nix-flake) and [source builds](#build-from-source) also offer builds without the UI.
**Windows** (PowerShell):
```powershell
@@ -136,7 +130,19 @@ Restart your coding agent. Say **"Index this project"**: done.
The `install` command automatically strips macOS quarantine attributes and ad-hoc signs the binary; no manual `xattr`/`codesign` needed.
</details>
-The `install` command auto-detects installed coding agents and configures their documented MCP entries plus durable instructions, skills, and lifecycle hooks where supported.
+### Agent setup: skills, profiles, and hooks
+
+Installation also equips supported coding agents to use the graph in daily work. The native `install` command detects clients and installs the integration pieces their documented formats support:
+
+| Component | What it adds |
+|-----------|--------------|
+| **MCP configuration** | Connects the client to the local server and its tools. |
+| **Instructions and skills** | Explains graph-first exploration, index freshness, coverage checks, and when to read source. |
+| **Scout, Verify, and Auditor profiles** | Offers fast provisional lookup, task-directed verification, or bounded full verification, where custom agents are supported. |
+| **Session and compaction hooks** | Restores graph context at supported lifecycle events. |
+| **Search and read hooks** | Adds relevant graph context to supported searches and flags recorded coverage gaps after supported file reads. |
+
+Hook augmentation is context-only and fail-open: it does not replace or block the requested tool call. Features vary by client and platform; some clients use durable instructions or a parent-agent handoff instead of hooks or direct subagent MCP access. Codex users review and trust installed hooks through `/hooks`. See [Multi-Agent Support](#multi-agent-support) and [Sessions, compaction, and subagents](#sessions-compaction-and-subagents) for exact support and activation requirements.
### Session Coordination Daemon
@@ -162,10 +168,10 @@ The ordinary `cli` mode runs one command locally, but it is not disconnected fro
### CBM Lens Beta: code visualization and source navigation
-CBM Lens Beta is the browser interface built into the binary. It builds on [CodeAtlasWeb](graph-ui/README.md) by [Bernhard Jackiewicz](https://github.com/BernhardJackiewicz) (design and tracking in #1964). It runs on loopback; the only request that leaves your machine is the optional model download from Hugging Face, and only after you start it. Each panel names where its facts come from, and what the index did not record is shown as a gap. Start the local server:
+CBM Lens Beta is the browser interface included in standard native releases and UI-enabled source builds. It builds on [CodeAtlasWeb](graph-ui/README.md) by [Bernhard Jackiewicz](https://github.com/BernhardJackiewicz) (design and tracking in #1964). Lens is served on loopback. Browser AI downloads its optional model only after you enable it; inference stays on-device. Each panel names where its facts come from, and what the index did not record is shown as a gap. Start the local server:
```bash
-./build/c/codebase-memory-mcp daemon start --open --port=9749
+codebase-memory-mcp daemon start --open --port=9749
```
The browser opens at `http://127.0.0.1:9749`. A permanent daemon keeps the UI available after the command exits. Use `daemon status` to inspect it and `daemon stop` when you are finished. For an MCP session, `--ui=true --port=9749` enables the same shared UI. Active clients must use the same executable build and cache directory.
@@ -246,7 +252,7 @@ Enable automatic indexing on MCP session start:
codebase-memory-mcp config set auto_index true
```
-When enabled, new projects are indexed automatically on first connection. Previously-indexed projects are registered with the background watcher for ongoing git-based change detection. Configurable file limit: `config set auto_index_limit 50000`.
+`auto_index` is off by default. When enabled, new projects are indexed automatically on first connection. The configurable file limit is `config set auto_index_limit 50000`. Previously indexed projects can be watched independently through `auto_watch` (on by default), subject to the session rules below.
The watcher follows MCP sessions: it watches the project each open MCP session is rooted in (the client's working directory) and stops when the last session for that project closes. A repository indexed with `cli index_repository`, or indexed from a session rooted somewhere else, is not watched; re-run `index_repository` after changing it. `index_status` reports this in its `watch` object: `watched`, and either the poll cadence and last scan time or the `reason` it is not watched.
@@ -299,9 +305,10 @@ The install script placed beside the binary is **reported, not deleted**: uninst
### Graph & analysis
- **Architecture overview**: `get_architecture` returns a compact summary by default. Request specific `aspects` for routes, hotspots, dependencies, clusters, or cycles. `system_structure` provides the projection used by CBM Lens and must be requested on its own.
-- **Architecture Decision Records**: `manage_adr` persists architectural decisions across sessions
+- **Architecture Decision Records**: `manage_adr` persists the project's decision record across sessions; indexing also extracts supported ADR metadata and supersession from documentation files
- **Louvain community detection**: Discovers functional modules by clustering call edges
-- **Git diff impact mapping**: `detect_changes` maps uncommitted changes to affected symbols with risk classification
+- **Change impact**: `detect_changes` maps uncommitted changes to affected symbols with risk classification and can report test impact with `scope: "tests"`; `compare_graphs` compares indexed snapshots
+- **Runtime observations**: `ingest_traces` adds observed call relationships from separately collected traces alongside static analysis; static call paths alone do not show what ran
- **Call graph**: Resolves function calls across files and packages (import-aware, type-inferred)
- **Dead code candidates**: find functions with no indexed callers, excluding entry points. Check dynamic dispatch, coverage gaps, and framework conventions before removing code.
- **Cypher-like queries**: `MATCH (f:Function)-[:CALLS]->(g) WHERE f.name = 'main' RETURN g.name`
@@ -312,6 +319,27 @@ The install script placed beside the binary is **reported, not deleted**: uninst
- **Structural search** (`search_graph`): regex name patterns, label filters, min/max degree, file scoping
- **Code search** (`search_code`): graph-augmented grep over indexed files only
+### Documentation connected to code
+
+Find the explanation behind a symbol and follow supported references back to its implementation. Documentation participates in the graph alongside source files:
+
+- **Markdown, reStructuredText, and AsciiDoc** become navigable document sections; **PDFs with text layers** become searchable text pages. PDF extraction does not perform OCR.
+- **Document-to-code references** and supported language doc-comment references create `MENTIONS` relationships when the target can be resolved.
+- **Architecture decision records** contribute metadata such as status, deciders, and supersession, so decisions can be explored with the code they describe.
+- **Supported diagrams and OpenAPI descriptions** contribute structured entities. Extraction and reference resolution differ by format; not every textual mention becomes a graph edge.
+
+Use graph and text search to locate the relevant section, follow its recorded relationships, and open the source evidence. Check `check_index_coverage` before treating a missing result as proof that the repository has no such documentation or reference.
+
+### Infrastructure and deployment
+
+Ask **"What deploys this service?"**, **"Which image runs it?"**, or **"Where does this configuration reach code?"** CBM connects supported infrastructure forms to the source they build, configure, and run:
+
+- **Containers and clusters**: Dockerfiles, Compose services, Kubernetes resources, Helm charts and releases, and Kustomize overlays and patches.
+- **Provisioning and configuration**: Terraform/OpenTofu resources and modules, tfvars overrides, Terragrunt dependencies, Ansible tasks and handlers, and supported configuration keys and environment-variable access.
+- **Build and delivery**: shell commands, Make targets, and supported CI steps that build images, invoke repository scripts, or deploy resources.
+
+For resolvable inputs, a trace can follow **Service → workload → image → Dockerfile → program**, or follow deployment and configuration relationships. Use `trace_path` modes for topology, deployment, and run paths. These are static relationships from supported source forms; dynamic values and unresolved templates can leave gaps. See [Edge types](#edge-types-selected) for the exact relationship rules and limitations.
+
### Cross-service linking
- **HTTP** route ↔ call-site matching with confidence scoring
- **gRPC, GraphQL, tRPC** service detection with protobuf Route extraction
@@ -323,6 +351,21 @@ The install script placed beside the binary is **reported, not deleted**: uninst
- **Run status**: `index_status` (and the UI layout next to `linked_projects`) carries a `cross_repo` object, `{"status":"never_run"}` until `index_repository(mode="cross-repo-intelligence")` has run with that project as the source, then `"ran"` with `last_run_at`, `outcome`, `targets`, `projects_scanned`, `total_cross_edges` and `skipped_projects`. That is how you tell "never linked" apart from "linked, nothing matched". The status is stored in the project's own index next to its `CROSS_*` edges, so a reindex that rebuilds the index drops both at once and the status goes back to `never_run`.
- **Skipped stores**: `target_projects: ["*"]` skips an index built before the #768 schema change rather than failing the whole run. The response lists each one as `skipped_projects: [{"name", "reason": "pre_768_schema", "hint": "reindex this project"}]`.
+### Smart CI and test impact
+
+Use the graph to explain which tests a change reaches, and use that evidence to focus supported CI runs. **Smart CI is experimental** and has two layers:
+
+| Layer | What it does | What you supply |
+|-------|--------------|-----------------|
+| **CI job selection** | Chooses jobs from the changed-file list. | Repository-specific path and job rules; this repository's selector is an example. |
+| **Test selection** | Combines static reachability, changed tests, and admitted per-test coverage to select suites or tests. | A supported C/C++ test harness, configuration, a coverage map, and a runner that accepts named selections. |
+
+`codebase-memory-mcp test-impact select` produces a selection with reasons; `test-impact publish` produces the graph-and-coverage bundle used as its baseline. For agent-assisted investigation, `detect_changes` with `scope: "tests"` exposes test impact through MCP.
+
+**Narrowing currently supports C/C++ family code with this repository's test conventions or declared equivalents.** It is not general test selection for every language CBM indexes. Missing, stale, incompatible, or incomplete evidence broadens the selection or returns `run_all`; static reachability without admitted coverage never omits a suite. Begin with report-only shadow mode and validate your harness before enabling gating.
+
+In this repository, test narrowing is wired to the Linux x86_64 test leg when `TEST_IMPACT_MODE=gate`; release and dry-run workflows retain full execution. See the [Smart CI guide](docs/SMART_CI.md) for supported conventions, coverage admission, setup, version requirements, and fallback behavior.
+
### Edge types (selected)
- `CALLS`: a callable is invoked at the source site
- `CALL_REFERENCE`: a callable is used at a supported reference site (for example, a direct value argument) and resolves to one exact target
@@ -426,7 +469,7 @@ Published backend benchmarks on Apple M3 Pro. These are separate from the CBM Le
**RAM-first pipeline**: All indexing runs in memory (LZ4 HC compressed read, in-memory SQLite, single dump at end). Memory is released back to the OS after indexing completes.
-**Token efficiency**: The project's [original README report](https://github.com/DeusData/codebase-memory-mcp/blob/4ff6feeab639c4668da0f491930326ed5ec63093/README.md#performance) lists ~3,400 tokens for five structural queries via codebase-memory-mcp versus ~412,000 via file-by-file exploration. That is approximately **120× fewer tokens**, or a **99.2% reduction**, for that comparison. The separate [31-repository study](https://arxiv.org/html/2603.27277v1#S4.SS1) reports a 10× token reduction. Its [system-performance measurements](https://arxiv.org/html/2603.27277v1#S4.SS3) include Linux kernel indexing in about 3 minutes and Cypher relationship queries under 1 ms on an Apple M3 Pro.
+**Token efficiency, within the reported workloads**: The project's [original README report](https://github.com/DeusData/codebase-memory-mcp/blob/4ff6feeab639c4668da0f491930326ed5ec63093/README.md#performance) lists ~3,400 tokens for five structural queries via codebase-memory-mcp versus ~412,000 via file-by-file exploration: approximately **120× fewer tokens** for that comparison. The separate [31-repository preprint](https://arxiv.org/html/2603.27277v1#S4.SS1) reports **10× lower token use** and **2.1× fewer tool calls**, with answer-quality scores of **83% for CBM versus 92% for file-by-file exploration**. These are scoped backend measurements, not a promised saving for every task or a benchmark of CBM Lens. Actual savings depend on the question, repository, agent, and required verification. The study's [system-performance measurements](https://arxiv.org/html/2603.27277v1#S4.SS3) include the Linux indexing and Cypher timings above.
To measure comparable quality, latency, and agent-efficiency metrics on your own workload, see [Measuring quality, latency, and agent savings](docs/MEASURING_SAVINGS.md). Exact reproduction of the figures above requires the original inputs and raw artifacts.
@@ -627,7 +670,7 @@ Restart your agent. Verify with `/mcp`; you should see `codebase-memory-mcp` wit
## Multi-Agent Support
-`install` configures 45 client surfaces: 39 detected automatically and 6
+`install` configures **45 supported automatic/conditional client surfaces**: 39 detected automatically and 6
conditional or explicit. “Conditional” means the installer writes only when the
documented platform or an explicit, already-existing config path proves the
target is active. It never flips experimental feature flags, enables plugins,
diff --git a/docs/index.html b/docs/index.html
index e39ded17e..2c48b3910 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -3,838 +3,440 @@
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>codebase-memory-mcp — Code Intelligence Knowledge Graph for AI Coding Agents</title>
- <meta name="description" content="codebase-memory-mcp is an open-source MCP server that indexes any codebase into a persistent knowledge graph so AI coding agents answer structural questions with ~120x fewer tokens. 162 languages, Hybrid LSP type resolution, local semantic vector search, code-clone detection, sub-1ms queries, Linux kernel indexed in 3 minutes. Native executable with verified assets and no language runtime. One command configures 45 automatic/conditional client surfaces.">
- <meta name="keywords" content="MCP server, code intelligence, knowledge graph, tree-sitter, Hybrid LSP, semantic code search, code embeddings, code clone detection, cross-repo analysis, data-flow analysis, Claude Code, Codex CLI, Gemini CLI, Cursor, Zed, code exploration, token reduction, call graph, dead code detection">
+ <title>Codebase Memory — Connect your code, docs and infrastructure</title>
+ <meta name="description" content="Local code intelligence for developers and AI agents. Connect code, documentation and infrastructure in a persistent graph. Explore CBM Lens, query 17 MCP tools, configure agent integrations, and investigate change and test impact.">
<meta name="author" content="DeusData">
<meta name="robots" content="index, follow, max-image-preview:large, max-snippet:-1">
- <meta name="theme-color" content="#0d1117">
-
- <!-- Open Graph -->
- <meta property="og:title" content="codebase-memory-mcp — Code Intelligence Knowledge Graph for AI Coding Agents">
- <meta property="og:description" content="Index any codebase into a persistent knowledge graph. AI agents answer structural questions with ~120x fewer tokens. 162 languages, Hybrid LSP, sub-1ms queries, native executable with verified assets.">
+ <meta name="theme-color" content="#0a0e0d">
+ <meta property="og:title" content="Codebase Memory — Understand the whole repository">
+ <meta property="og:description" content="Connect code, docs and infrastructure. Explore the graph in CBM Lens, give your agent structural context, and follow the impact of a change.">
<meta property="og:type" content="website">
<meta property="og:url" content="https://deusdata.github.io/codebase-memory-mcp/">
- <meta property="og:image" content="https://deusdata.github.io/codebase-memory-mcp/graph-ui-screenshot.png">
- <meta property="og:image:width" content="1538">
- <meta property="og:image:height" content="932">
- <meta property="og:image:alt" content="3D knowledge-graph visualization of a codebase with thousands of nodes and edges">
- <meta property="og:site_name" content="codebase-memory-mcp">
-
- <!-- Twitter Card -->
+ <meta property="og:image" content="https://deusdata.github.io/codebase-memory-mcp/images/lens-architecture.png">
+ <meta property="og:image:alt" content="CBM Lens architecture view of the codebase-memory-mcp repository">
+ <meta property="og:site_name" content="Codebase Memory">
<meta name="twitter:card" content="summary_large_image">
- <meta name="twitter:title" content="codebase-memory-mcp — Code Intelligence for AI Coding Agents">
- <meta name="twitter:description" content="Index any codebase into a knowledge graph. ~120x fewer tokens for AI code exploration. 162 languages, Hybrid LSP, sub-1ms queries, native executable with verified assets.">
- <meta name="twitter:image" content="https://deusdata.github.io/codebase-memory-mcp/graph-ui-screenshot.png">
-
+ <meta name="twitter:title" content="Codebase Memory — Understand the whole repository">
+ <meta name="twitter:description" content="Local code intelligence for developers and AI agents. Code, docs, infrastructure, CBM Lens and experimental Smart CI.">
+ <meta name="twitter:image" content="https://deusdata.github.io/codebase-memory-mcp/images/lens-architecture.png">
<link rel="canonical" href="https://deusdata.github.io/codebase-memory-mcp/">
- <link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 32 32'%3E%3Crect width='32' height='32' rx='6' fill='%230d1117'/%3E%3Cg stroke='%2358a6ff' stroke-width='2'%3E%3Cline x1='9' y1='9' x2='23' y2='16'/%3E%3Cline x1='23' y1='16' x2='10' y2='24'/%3E%3Cline x1='9' y1='9' x2='10' y2='24'/%3E%3C/g%3E%3Cg fill='%2358a6ff'%3E%3Ccircle cx='9' cy='9' r='3.5'/%3E%3Ccircle cx='23' cy='16' r='3.5'/%3E%3Ccircle cx='10' cy='24' r='3.5'/%3E%3C/g%3E%3C/svg%3E">
-
- <!-- Structured data: SoftwareApplication (the tool) -->
+ <link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 32 32'%3E%3Crect width='32' height='32' rx='6' fill='%230a0e0d'/%3E%3Cg stroke='%2333ff99' stroke-width='2'%3E%3Cpath d='M9 9L23 16L10 24Z' fill='none'/%3E%3C/g%3E%3Cg fill='%2333ff99'%3E%3Ccircle cx='9' cy='9' r='3.5'/%3E%3Ccircle cx='23' cy='16' r='3.5'/%3E%3Ccircle cx='10' cy='24' r='3.5'/%3E%3C/g%3E%3C/svg%3E">
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "SoftwareApplication",
"name": "codebase-memory-mcp",
- "alternateName": "Codebase Memory MCP",
+ "alternateName": "Codebase Memory",
"applicationCategory": "DeveloperApplication",
- "applicationSubCategory": "Model Context Protocol (MCP) server",
"operatingSystem": "macOS, Linux, Windows",
- "softwareVersion": "0.8.1",
- "description": "An open-source MCP server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links, so AI coding agents answer structural questions with roughly 120x fewer tokens than file-by-file search. Parses 162 languages via tree-sitter with Hybrid LSP semantic type resolution for 9 language families. Ships as a native executable with authenticated release-owned assets; the native install needs no language runtime.",
+ "description": "Local code intelligence connecting source code, documentation and infrastructure in a persistent knowledge graph, with CBM Lens, MCP tools, agent integrations and experimental C/C++ test selection.",
"url": "https://deusdata.github.io/codebase-memory-mcp/",
"downloadUrl": "https://github.com/DeusData/codebase-memory-mcp/releases/latest",
"codeRepository": "https://github.com/DeusData/codebase-memory-mcp",
"programmingLanguage": "C",
"license": "https://opensource.org/licenses/MIT",
"isAccessibleForFree": true,
- "offers": {
- "@type": "Offer",
- "price": "0",
- "priceCurrency": "USD"
- },
+ "offers": { "@type": "Offer", "price": "0", "priceCurrency": "USD" },
"featureList": [
- "Indexes 158 programming languages via vendored tree-sitter grammars",
- "Hybrid LSP semantic type resolution for Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust",
- "17 MCP tools for structural search, call-path tracing, targeted coverage checks, and Cypher graph queries",
- "Semantic vector code search via bundled nomic-embed-code embeddings (no API key, fully local)",
- "Semantic graph edges (SEMANTICALLY_RELATED) and near-clone detection (SIMILAR_TO, MinHash + LSH)",
- "Cross-service linking for HTTP, gRPC, GraphQL, tRPC, and pub/sub channels with confidence scoring",
- "Cross-repo intelligence with CROSS_* edges across multiple indexed repositories",
- "Data-flow tracing with argument-to-parameter mapping",
- "Change-impact analysis mapping git diffs to affected symbols and blast radius",
- "Architecture Decision Record (ADR) persistence across sessions",
- "Dead-code detection with entry-point filtering",
- "Infrastructure-as-code indexing for Dockerfiles, Kubernetes, and Kustomize",
- "Built-in 3D graph visualization UI",
- "Auto-sync background watcher for incremental re-indexing",
- "One command configures 45 automatic/conditional client surfaces"
+ "Persistent local graph of code, documentation and infrastructure",
+ "Structural, full-text and local semantic search",
+ "Hybrid LSP semantic type resolution for supported language families",
+ "17 MCP tools, CLI access and Cypher graph queries",
+ "CBM Lens source navigation, architecture maps and Galaxy graph",
+ "Documentation sections, PDF text pages and architecture decision records",
+ "Static infrastructure, deployment and configuration relationships",
+ "Cross-service and cross-repository linking",
+ "Change impact, coverage diagnostics and optional runtime trace ingestion",
+ "Experimental C/C++ test selection using static relationships and admitted per-test coverage",
+ "45 automatic/conditional client surfaces with client-specific setup",
+ "Optional browser AI with on-device inference"
],
- "author": {
- "@type": "Organization",
- "name": "DeusData",
- "url": "https://github.com/DeusData"
- },
- "citation": {
- "@type": "ScholarlyArticle",
- "name": "Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP",
- "identifier": "arXiv:2603.27277",
- "url": "https://arxiv.org/abs/2603.27277"
- }
- }
- </script>
-
- <!-- Structured data: Organization + WebSite identity -->
- <script type="application/ld+json">
- {
- "@context": "https://schema.org",
- "@graph": [
- {
- "@type": "Organization",
- "@id": "https://deusdata.github.io/codebase-memory-mcp/#org",
- "name": "DeusData",
- "url": "https://github.com/DeusData",
- "sameAs": ["https://github.com/DeusData/codebase-memory-mcp"]
- },
- {
- "@type": "WebSite",
- "@id": "https://deusdata.github.io/codebase-memory-mcp/#website",
- "url": "https://deusdata.github.io/codebase-memory-mcp/",
- "name": "codebase-memory-mcp",
- "publisher": { "@id": "https://deusdata.github.io/codebase-memory-mcp/#org" }
- },
- {
- "@type": "BreadcrumbList",
- "itemListElement": [
- { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://deusdata.github.io/codebase-memory-mcp/" },
- { "@type": "ListItem", "position": 2, "name": "GitHub", "item": "https://github.com/DeusData/codebase-memory-mcp" }
- ]
- }
- ]
- }
- </script>
-
- <!-- Structured data: FAQPage (machine-readable Q&A for answer engines) -->
- <script type="application/ld+json">
- {
- "@context": "https://schema.org",
- "@type": "FAQPage",
- "mainEntity": [
- {
- "@type": "Question",
- "name": "What is codebase-memory-mcp?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "codebase-memory-mcp is an open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. AI coding agents query that graph instead of reading files one by one, answering structural questions with roughly 120x fewer tokens. It parses 162 languages and ships as a native executable with authenticated release-owned assets; the native install needs no language runtime."
- }
- },
- {
- "@type": "Question",
- "name": "How does codebase-memory-mcp reduce token usage?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "AI agents normally explore code through repeated grep-then-read cycles, which burn large numbers of tokens. codebase-memory-mcp answers the same structural questions from a precomputed graph. In a five-query benchmark it used about 3,400 tokens versus about 412,000 tokens for file-by-file search — a roughly 120x reduction."
- }
- },
- {
- "@type": "Question",
- "name": "Which programming languages does codebase-memory-mcp support?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "It supports 162 languages through vendored tree-sitter grammars compiled into the binary, including Python, Go, JavaScript, TypeScript, Rust, Java, C, C++, C#, PHP, Ruby, Kotlin, Swift, and many more. Nine language families — Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust — additionally get Hybrid LSP semantic type resolution."
- }
- },
- {
- "@type": "Question",
- "name": "What is Hybrid LSP?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "Hybrid LSP is a lightweight C implementation of language type-resolution algorithms, structurally inspired by and compatible with major language servers (tsserver, pyright, gopls, Roslyn), embedded directly into the binary. It runs alongside tree-sitter to resolve imports, generics, inheritance, and stdlib types — so call edges in the graph mirror what an IDE 'Go to Definition' would resolve, with no language-server process or per-project setup."
- }
- },
- {
- "@type": "Question",
- "name": "Which AI coding agents work with codebase-memory-mcp?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "A single install command configures 45 automatic/conditional client surfaces. The 39 detected surfaces are Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp). Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody are conditional or explicit integrations. Qodo, Warp MCP, JetBrains AI/ACP, GitHub Copilot coding agent, Jules, CodeRabbit, Replit, BLACKBOX AI, Plandex, and SWE-agent require manual, UI, cloud, or repository-managed setup and are not counted among the 45."
- }
- },
- {
- "@type": "Question",
- "name": "Does codebase-memory-mcp send my code anywhere?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "No. All indexing and querying happen 100% locally on your machine. There is no embedded LLM and no API key — your MCP client acts as the intelligence layer. Before release testing, three behaviourally identical executable candidates (unstripped, debug-stripped, stripped) for every platform and link mode are submitted to VirusTotal. The selected candidate is packaged with its SHA-256 unchanged, and release notes link every measured result. Publication permits only the documented single-Microsoft !ml tolerance."
- }
- },
- {
- "@type": "Question",
- "name": "Does codebase-memory-mcp support semantic or natural-language code search?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "Yes. Alongside structural and BM25 full-text search, it offers semantic vector search over the whole graph via the search_graph tool's semantic_query parameter. It is powered by nomic-embed-code embeddings compiled directly into the binary (768-dimensional), so it bridges vocabulary gaps — finding 'publish' when you search 'send' — with no API key, no Ollama, and no Docker. The indexer also generates SEMANTICALLY_RELATED edges between conceptually similar functions and SIMILAR_TO edges for near-duplicate and clone detection."
- }
- },
- {
- "@type": "Question",
- "name": "Can codebase-memory-mcp detect duplicate or near-clone code?",
- "acceptedAnswer": {
- "@type": "Answer",
- "text": "Yes. During indexing it builds SIMILAR_TO edges using MinHash plus LSH with Jaccard scoring, surfacing near-duplicate and copy-pasted functions across the codebase. Combined with SEMANTICALLY_RELATED edges, this makes refactoring candidates and redundant implementations queryable through the graph."
- }
- }
- ]
+ "author": { "@type": "Organization", "name": "DeusData", "url": "https://github.com/DeusData" }
}
</script>
-
<style>
:root {
- --bg: #0d1117;
- --surface: #161b22;
- --border: #30363d;
- --text: #e6edf3;
- --text-secondary: #8b949e;
- --accent: #58a6ff;
- --accent-hover: #79c0ff;
- --green: #3fb950;
- --red: #f85149;
- }
- * { margin: 0; padding: 0; box-sizing: border-box; }
- body {
- font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif;
- background: var(--bg);
- color: var(--text);
- line-height: 1.6;
- }
- a { color: var(--accent); }
- .container { max-width: 960px; margin: 0 auto; padding: 0 24px; }
- .muted { color: var(--text-secondary); }
- cite { color: var(--text-secondary); font-style: normal; font-size: 0.8rem; }
- cite a { color: var(--text-secondary); }
-
- /* Nav */
- nav {
- border-bottom: 1px solid var(--border);
- position: sticky;
- top: 0;
- background: rgba(13,17,23,0.85);
- backdrop-filter: blur(8px);
- z-index: 10;
- }
- nav .container {
- display: flex;
- align-items: center;
- justify-content: center;
- height: 56px;
- }
- nav .links a {
- text-decoration: none;
- color: var(--text-secondary);
- margin-left: 20px;
- font-size: 0.9rem;
+ color-scheme: dark;
+ --bg: #0a0e0d; --panel: #0f1513; --raised: #131b18; --line: #243a30;
+ --green: #33ff99; --muted: #9eb5a8; --text: #dce8e1; --cyan: #66d9e8; --selected: #12251d;
+ --mono: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace;
}
- nav .links a:hover { color: var(--text); }
- nav .links a:first-child { margin-left: 0; }
- nav .links a.nav-star { color: var(--green); font-weight: 600; }
- nav .links a.nav-star:hover { color: var(--accent-hover); }
- @media (max-width: 640px) { nav .links a:not(.nav-cta) { display: none; } }
-
- /* Hero */
- .hero { padding: 72px 0 32px; text-align: center; }
- .hero h1 { font-size: 2.5rem; font-weight: 700; margin-bottom: 4px; }
- .hero .by-line { color: #6e7681; font-size: 0.95rem; margin-bottom: 24px; }
- .hero .tagline {
- font-size: 1.2rem;
- color: var(--text-secondary);
- margin: 0 auto 32px;
- max-width: 720px;
- }
- .hero .stat {
- display: inline-block;
- background: var(--surface);
- border: 1px solid var(--border);
- border-radius: 8px;
- padding: 16px 24px;
- margin: 8px;
- }
- .hero .stat .number { font-size: 2rem; font-weight: 700; color: var(--accent); }
- .hero .stat .label { font-size: 0.875rem; color: var(--text-secondary); }
- .cta-buttons { margin-top: 32px; }
- .cta-buttons a {
- display: inline-block;
- padding: 12px 24px;
- border-radius: 6px;
- text-decoration: none;
- font-weight: 600;
- margin: 4px;
- }
- .cta-primary { background: var(--accent); color: #0d1117; }
- .cta-primary:hover { background: var(--accent-hover); }
- .cta-secondary { border: 1px solid var(--border); color: var(--text); }
- .cta-secondary:hover { border-color: var(--text-secondary); }
-
- /* Screenshot */
- .screenshot { margin: 40px 0; text-align: center; }
- .screenshot img {
- max-width: 100%;
- height: auto;
- border-radius: 12px;
- border: 1px solid var(--border);
- box-shadow: 0 8px 32px rgba(0,0,0,0.4);
- }
- .screenshot .caption { margin-top: 12px; font-size: 0.875rem; color: var(--text-secondary); }
-
- /* Research callout */
- .research {
- display: flex;
- align-items: center;
- gap: 20px;
- flex-wrap: wrap;
- background: var(--surface);
- border: 1px solid var(--border);
- border-left: 3px solid var(--accent);
- border-radius: 8px;
- padding: 20px 24px;
- margin: 8px 0 0;
- }
- .research .arxiv-badge {
- display: inline-flex;
- align-items: center;
- gap: 8px;
- flex-shrink: 0;
- font-family: 'SF Mono', monospace;
- font-size: 0.8rem;
- font-weight: 700;
- color: #b31b1b;
- background: #fff;
- border-radius: 6px;
- padding: 8px 12px;
- text-decoration: none;
- }
- .research p { font-size: 0.92rem; margin: 0; }
- .research .label { color: var(--accent); font-weight: 700; }
-
- /* Sections */
- section { padding: 56px 0; border-top: 1px solid var(--border); }
- section h2 { font-size: 1.75rem; margin-bottom: 8px; scroll-margin-top: 72px; }
- section .lead { font-size: 1.05rem; margin-bottom: 24px; }
- section h3 { font-size: 1.1rem; margin: 24px 0 8px; }
-
- /* Code / install */
- .install-block {
- background: var(--surface);
- border: 1px solid var(--border);
- border-radius: 8px;
- padding: 20px 24px;
- font-family: 'SF Mono', 'Fira Code', monospace;
- font-size: 0.9rem;
- overflow-x: auto;
- margin: 16px 0;
- }
- .install-block .comment { color: var(--text-secondary); }
- .install-block .cmd { color: var(--green); }
- code {
- font-family: 'SF Mono', 'Fira Code', monospace;
- background: var(--surface);
- border: 1px solid var(--border);
- border-radius: 4px;
- padding: 1px 6px;
- font-size: 0.85em;
- }
-
- /* Tables */
- table { width: 100%; border-collapse: collapse; margin: 16px 0; }
- th, td { padding: 10px 16px; text-align: left; border-bottom: 1px solid var(--border); }
- th {
- background: var(--surface);
- font-weight: 600;
- font-size: 0.875rem;
- color: var(--text-secondary);
- text-transform: uppercase;
- letter-spacing: 0.5px;
- }
- td { font-size: 0.9rem; }
- .win { color: var(--green); font-weight: 600; }
- .benchmark-table td:nth-child(2), .benchmark-table td:nth-child(3), .benchmark-table td:nth-child(4) {
- text-align: right; font-family: 'SF Mono', monospace; font-size: 0.85rem;
- }
- .benchmark-table th:nth-child(2), .benchmark-table th:nth-child(3), .benchmark-table th:nth-child(4) { text-align: right; }
-
- /* Features grid */
- .features {
- display: grid;
- grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));
- gap: 20px;
- margin-top: 24px;
- }
- .feature {
- background: var(--surface);
- border: 1px solid var(--border);
- border-radius: 8px;
- padding: 24px;
- }
- .feature h3 { font-size: 1rem; margin: 0 0 8px; }
- .feature p { font-size: 0.875rem; color: var(--text-secondary); }
-
- /* Hybrid LSP table */
- .lsp-table td:first-child { font-weight: 600; white-space: nowrap; }
- .lsp-table td { vertical-align: top; }
-
- /* Releases */
- .release {
- background: var(--surface);
- border: 1px solid var(--border);
- border-radius: 8px;
- padding: 16px 20px;
- margin: 12px 0;
- }
- .release-head { display: flex; align-items: baseline; justify-content: space-between; flex-wrap: wrap; gap: 8px; }
- .release-tag { font-weight: 700; font-size: 1.05rem; }
- .release-date { color: var(--text-secondary); font-size: 0.85rem; }
- .release details { margin-top: 10px; }
- .release summary { cursor: pointer; color: var(--accent); font-size: 0.9rem; }
- .release-body { margin-top: 12px; font-size: 0.875rem; color: var(--text-secondary); }
- .release-body h4, .release-body h5, .release-body h6 { font-size: 0.95rem; color: var(--text); margin: 12px 0 6px; }
- .release-body ul { margin: 6px 0 6px 20px; }
- .release-body code { font-size: 0.8em; }
- .skeleton { color: var(--text-secondary); font-size: 0.9rem; }
-
- /* FAQ */
- .faq h3 { font-size: 1.05rem; margin: 24px 0 6px; }
- .faq p { color: var(--text-secondary); margin-bottom: 8px; }
-
- /* Footer */
- footer {
- padding: 40px 0;
- text-align: center;
- color: var(--text-secondary);
- font-size: 0.875rem;
- border-top: 1px solid var(--border);
+ * { box-sizing: border-box; }
+ html { scroll-behavior: smooth; scroll-padding-top: 100px; }
+ body { margin: 0; background: var(--bg); color: var(--text); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif; font-size: 16px; line-height: 1.65; }
+ a { color: var(--green); text-decoration: none; text-underline-offset: 4px; }
+ a:hover { text-decoration: underline; }
+ a:focus-visible, summary:focus-visible { outline: 2px solid var(--green); outline-offset: 5px; }
+ ::selection { background: var(--green); color: var(--bg); }
+ img { max-width: 100%; height: auto; display: block; }
+ p { margin: 0 0 20px; }
+ h1, h2, h3 { color: #edf5f0; line-height: 1.12; letter-spacing: -.035em; margin: 0; font-weight: 600; }
+ h1 { font-size: clamp(48px, 6.3vw, 84px); max-width: 820px; }
+ h2 { font-size: clamp(32px, 4vw, 49px); max-width: 800px; }
+ h3 { font-size: 22px; line-height: 1.3; }
+ code { font-family: var(--mono); font-size: .87em; overflow-wrap: anywhere; color: #c3decf; }
+ p code, li code { padding: 2px 5px; border: 1px solid var(--line); border-radius: 4px; background: var(--panel); }
+ pre { margin: 0; white-space: pre-wrap; overflow-wrap: anywhere; }
+ pre code { font-size: 13px; line-height: 1.9; }
+ .container { width: min(1180px, calc(100% - 64px)); margin: 0 auto; }
+ .skip { position: absolute; top: -80px; left: 20px; padding: 10px 20px; background: var(--green); color: var(--bg); z-index: 10; }
+ .skip:focus { top: 10px; }
+ .site-header { position: sticky; top: 0; z-index: 5; border-bottom: 1px solid var(--line); background: rgba(10,14,13,.95); backdrop-filter: blur(16px); }
+ .nav { display: flex; align-items: center; justify-content: space-between; min-height: 76px; gap: 28px; }
+ .brand { display: flex; align-items: center; gap: 10px; font-weight: 600; color: var(--text); letter-spacing: -.025em; white-space: nowrap; }
+ .brand svg { width: 27px; height: 27px; color: var(--green); }
+ .nav-links { display: flex; gap: 28px; align-items: center; font-size: 13px; }
+ .nav-links a { color: var(--muted); }
+ .nav-links a:hover { color: var(--green); }
+ .nav-links .nav-install { border: 1px solid var(--line); border-radius: 6px; padding: 8px 15px; color: var(--text); }
+ .eyebrow { font-family: var(--mono); font-size: 11px; font-weight: 500; letter-spacing: .12em; text-transform: uppercase; color: var(--green); margin-bottom: 23px; }
+ .hero { padding: 80px 0 0; }
+ .hero-top { display: grid; grid-template-columns: 1fr 270px; gap: 65px; align-items: end; }
+ .hero h1 span { color: var(--green); }
+ .hero-intro { color: var(--muted); max-width: 690px; font-size: 19px; line-height: 1.6; margin-top: 28px; }
+ .hero-aside { padding: 0 0 8px 24px; border-left: 1px solid var(--line); color: var(--muted); font-size: 14px; }
+ .hero-aside strong { display: block; color: var(--text); font-weight: 500; margin: 15px 0 2px; }
+ .hero-aside p { margin: 0; }
+ .actions { display: flex; flex-wrap: wrap; align-items: center; gap: 12px; margin: 30px 0 20px; }
+ .button { display: inline-flex; justify-content: center; align-items: center; gap: 20px; min-height: 47px; padding: 10px 22px; border-radius: 6px; font-size: 14px; font-weight: 600; border: 1px solid var(--line); color: var(--text); background: var(--raised); }
+ .button:hover { text-decoration: none; border-color: var(--green); }
+ .button.primary { color: #062014; border-color: var(--green); background: var(--green); }
+ .hero-note { color: var(--muted); font-family: var(--mono); font-size: 11px; }
+ .product-shot { margin: 48px 0 0; border: 1px solid var(--line); border-radius: 10px; overflow: hidden; background: var(--panel); box-shadow: 0 24px 80px rgba(0,0,0,.3); }
+ .shot-bar { display: flex; justify-content: space-between; align-items: center; gap: 15px; padding: 12px 18px; border-bottom: 1px solid var(--line); font-family: var(--mono); font-size: 10px; color: var(--muted); }
+ .shot-bar .live { color: var(--green); }
+ .shot-bar .live:before { content: ""; display: inline-block; width: 6px; height: 6px; background: var(--green); border-radius: 100%; margin-right: 8px; }
+ .product-shot img { width: 100%; }
+ figcaption { font-size: 12px; color: var(--muted); padding: 13px 18px; border-top: 1px solid var(--line); }
+ .facts { display: grid; grid-template-columns: repeat(4, 1fr); padding: 30px 0; border-bottom: 1px solid var(--line); gap: 24px; }
+ .facts strong { display: block; font-size: 22px; font-weight: 500; letter-spacing: -.03em; }
+ .facts span { font-size: 12px; color: var(--muted); }
+ .section { padding: 100px 0; border-bottom: 1px solid var(--line); }
+ .section-head { display: flex; justify-content: space-between; align-items: end; gap: 60px; margin-bottom: 42px; }
+ .section-head p { max-width: 370px; color: var(--muted); margin: 0; font-size: 15px; }
+ .section-head .eyebrow { margin-bottom: 17px; }
+ .intro { max-width: 740px; margin-top: 24px; color: var(--muted); font-size: 18px; }
+ .connection-grid { display: grid; grid-template-columns: repeat(3, 1fr); gap: 42px; }
+ .connection { border-top: 2px solid var(--line); padding-top: 25px; }
+ .connection .number { font: 11px var(--mono); color: var(--green); margin-bottom: 22px; display: block; }
+ .connection p { font-size: 14px; color: var(--muted); margin: 18px 0; }
+ .connection ul { padding-left: 18px; margin: 0; font-size: 13px; color: var(--muted); }
+ .connection li { margin-bottom: 8px; }
+ .source-link { display: inline-block; margin-top: 18px; font-size: 13px; }
+ .trace-strip { display: flex; flex-wrap: wrap; align-items: center; gap: 12px; padding: 25px 28px; margin: 35px 0 0; border: 1px solid var(--line); background: var(--panel); border-radius: 8px; }
+ .trace-strip span { font-family: var(--mono); font-size: 12px; }
+ .trace-strip .arrow { color: var(--green); }
+ .trace-strip .trace-label { color: var(--muted); margin-right: auto; }
+ .fine { color: var(--muted); font-size: 12px; margin-top: 16px; }
+ .lens-grid { display: grid; grid-template-columns: 1.5fr 1fr; gap: 35px; align-items: center; }
+ .lens-grid figure { margin: 0; border: 1px solid var(--line); border-radius: 8px; overflow: hidden; background: var(--panel); }
+ .lens-copy { padding-left: 15px; }
+ .lens-copy h3 { margin: 24px 0 12px; font-size: 20px; }
+ .lens-copy h3:first-child { margin-top: 0; }
+ .lens-copy p { color: var(--muted); font-size: 14px; }
+ .gallery { display: grid; grid-template-columns: repeat(3, 1fr); gap: 24px; margin-top: 38px; }
+ .gallery figure { margin: 0; border: 1px solid var(--line); border-radius: 7px; overflow: hidden; background: var(--panel); }
+ .gallery a { display: block; }
+ .gallery img { width: 100%; aspect-ratio: 16/10; object-fit: cover; object-position: top left; }
+ .gallery figcaption { padding: 14px 16px; }
+ .gallery strong { display: block; color: var(--text); font-weight: 500; margin-bottom: 4px; }
+ .feature-row { display: grid; grid-template-columns: 240px 1fr; gap: 60px; border-top: 1px solid var(--line); padding: 30px 0; }
+ .feature-row h3 { font-size: 20px; }
+ .feature-row p { color: var(--muted); font-size: 15px; margin-bottom: 12px; }
+ .feature-row p:last-child { margin-bottom: 0; }
+ .feature-row .tags { display: flex; flex-wrap: wrap; gap: 8px; }
+ .tag { border: 1px solid var(--line); border-radius: 4px; padding: 3px 8px; font: 10px var(--mono); color: var(--muted); }
+ .split { display: grid; grid-template-columns: 1fr 1fr; gap: 65px; align-items: start; }
+ .split p { color: var(--muted); }
+ .split h2 { margin-bottom: 25px; }
+ .ci-panel { border: 1px solid var(--line); background: var(--panel); border-radius: 8px; overflow: hidden; }
+ .ci-title { padding: 13px 22px; border-bottom: 1px solid var(--line); color: var(--muted); font: 11px var(--mono); }
+ .ci-step { display: grid; grid-template-columns: 25px 1fr; gap: 15px; padding: 21px 22px; border-bottom: 1px solid var(--line); }
+ .ci-step:last-child { border-bottom: none; }
+ .ci-step .number { color: var(--green); font: 12px var(--mono); padding-top: 3px; }
+ .ci-step strong { display: block; font-size: 14px; font-weight: 500; }
+ .ci-step p { font-size: 12px; margin: 5px 0 0; }
+ .ci-step.fallback { background: var(--selected); }
+ .label { display: inline-block; font: 10px var(--mono); color: var(--cyan); border: 1px solid #31555b; padding: 4px 7px; border-radius: 4px; margin-left: 10px; vertical-align: middle; letter-spacing: .02em; }
+ .integration-flow { display: grid; grid-template-columns: repeat(3, 1fr); margin: 35px 0; border: 1px solid var(--line); border-radius: 8px; overflow: hidden; }
+ .integration-step { padding: 24px; background: var(--panel); border-right: 1px solid var(--line); }
+ .integration-step:last-child { border-right: none; }
+ .integration-step strong { font-size: 16px; font-weight: 500; }
+ .integration-step .number { display: block; color: var(--green); font: 11px var(--mono); margin-bottom: 15px; }
+ .integration-step p { font-size: 13px; color: var(--muted); margin: 12px 0 0; }
+ details { border-top: 1px solid var(--line); padding: 20px 0; }
+ summary { cursor: pointer; font-size: 15px; font-weight: 500; }
+ details p { color: var(--muted); font-size: 14px; margin: 18px 0 0; }
+ details p:last-child { margin-bottom: 0; }
+ .tool-list { display: flex; flex-wrap: wrap; gap: 8px; margin-top: 22px; }
+ .tool-list code { padding: 5px 8px; border: 1px solid var(--line); border-radius: 4px; font-size: 11px; }
+ .terminal { border: 1px solid var(--line); border-radius: 8px; overflow: hidden; background: var(--panel); }
+ .terminal-head { padding: 12px 22px; border-bottom: 1px solid var(--line); font: 11px var(--mono); color: var(--muted); }
+ .terminal pre { padding: 25px; }
+ .comment { color: var(--muted); }
+ .command { color: var(--green); }
+ .install-links { display: flex; flex-wrap: wrap; gap: 18px; margin-top: 20px; font-size: 13px; }
+ .install-copy h3 { margin: 8px 0 16px; }
+ .install-copy p { font-size: 14px; }
+ .install-copy .button { margin-top: 7px; }
+ .evidence { display: grid; grid-template-columns: 1.1fr 1fr; gap: 65px; }
+ .evidence h2 { font-size: 35px; }
+ .evidence p { color: var(--muted); font-size: 15px; }
+ .evidence-links { display: flex; flex-wrap: wrap; gap: 12px 25px; font-size: 13px; }
+ .faq { max-width: 900px; }
+ .faq h2 { margin-bottom: 35px; }
+ .release { border-top: 1px solid var(--line); padding: 20px 0; }
+ .release-head { display: flex; justify-content: space-between; gap: 25px; align-items: start; }
+ .release-tag { font-size: 15px; }
+ .release-date { color: var(--muted); font: 11px var(--mono); white-space: nowrap; padding-top: 5px; }
+ .release details { border-top: none; padding: 12px 0 0; }
+ .release summary { font-size: 12px; color: var(--muted); }
+ .release-body { color: var(--muted); font-size: 13px; }
+ .release-body h4, .release-body h5, .release-body h6 { color: var(--text); font-size: 14px; margin: 18px 0 10px; }
+ .release-body p { font-size: 13px; margin: 10px 0; }
+ .release-body a { overflow-wrap: anywhere; }
+ .skeleton { color: var(--muted); font-size: 14px; }
+ footer { padding: 35px 0 45px; }
+ .footer-inner { display: flex; justify-content: space-between; gap: 30px; align-items: start; }
+ footer p { color: var(--muted); font-size: 12px; margin: 7px 0 0; }
+ .footer-links { display: flex; flex-wrap: wrap; gap: 20px; font-size: 12px; }
+ @media (max-width: 950px) {
+ .hero-top { grid-template-columns: 1fr; gap: 25px; }
+ .hero-aside { display: none; }
+ .nav-links { gap: 17px; }
+ .section-head { align-items: start; gap: 30px; }
+ .section-head p { max-width: 300px; }
+ .connection-grid { gap: 24px; }
+ .split { gap: 35px; }
+ .lens-grid { grid-template-columns: 1fr; }
+ .lens-copy { padding: 0; display: grid; grid-template-columns: 1fr 1fr; gap: 28px; }
+ .lens-copy h3 { margin-top: 0; }
+ .feature-row { grid-template-columns: 200px 1fr; gap: 30px; }
}
- footer a { color: var(--accent); text-decoration: none; }
-
- @media (max-width: 640px) {
- .hero h1 { font-size: 1.75rem; }
- .hero .stat { display: block; margin: 8px 0; }
+ @media (max-width: 680px) {
+ .container { width: calc(100% - 36px); }
+ .nav { min-height: 65px; gap: 12px; }
+ .brand { font-size: 14px; }
+ .brand svg { width: 23px; }
+ .nav-links { gap: 12px; font-size: 12px; }
+ .nav-links .desktop-link { display: none; }
+ .nav-links .nav-install { padding: 7px 12px; }
+ .hero { padding-top: 50px; }
+ h1 { font-size: clamp(42px, 10.5vw, 64px); }
+ .hero-intro { font-size: 17px; }
+ .hero-note { font-size: 10px; }
+ .hero .actions { gap: 10px; }
+ .button { padding: 10px 17px; gap: 12px; }
+ .product-shot { margin-top: 35px; }
+ .shot-bar { font-size: 9px; padding: 10px 12px; }
+ .shot-bar .shot-path { display: none; }
+ figcaption { font-size: 11px; padding: 12px; }
+ .facts { grid-template-columns: 1fr 1fr; gap: 22px; }
+ .facts strong { font-size: 20px; }
+ .section { padding: 65px 0; }
+ .section-head { display: block; margin-bottom: 30px; }
+ .section-head p { max-width: none; margin-top: 20px; }
+ .connection-grid, .split, .evidence { grid-template-columns: 1fr; gap: 35px; }
+ .connection { padding-top: 20px; }
+ .connection .number { margin-bottom: 13px; }
+ .connection p { margin: 12px 0; }
+ .trace-strip { gap: 9px; padding: 20px; }
+ .trace-strip .trace-label { flex-basis: 100%; margin-bottom: 5px; }
+ .trace-strip span { font-size: 10px; }
+ .lens-copy { grid-template-columns: 1fr; gap: 10px; }
+ .gallery { grid-template-columns: 1fr; gap: 22px; }
+ .gallery img { aspect-ratio: auto; object-fit: contain; }
+ .feature-row { grid-template-columns: 1fr; gap: 16px; }
+ .integration-flow { grid-template-columns: 1fr; }
+ .integration-step { border-right: none; border-bottom: 1px solid var(--line); }
+ .integration-step:last-child { border-bottom: none; }
+ .terminal pre { padding: 18px; }
+ .terminal pre code { font-size: 11px; }
+ .release-head { flex-direction: column; gap: 4px; }
+ .footer-inner { flex-direction: column; gap: 22px; }
}
+ @media (prefers-reduced-motion: reduce) { html { scroll-behavior: auto; } }
</style>
</head>
<body>
-
-<nav>
- <div class="container">
- <span class="links">
- <a href="#what-is-it">What is it</a>
- <a href="#install">Install</a>
- <a href="#hybrid-lsp">Hybrid LSP</a>
- <a href="#semantic-search">Semantic search</a>
- <a href="#releases">Releases</a>
- <a href="#faq">FAQ</a>
- <a class="nav-cta nav-star" href="https://github.com/DeusData/codebase-memory-mcp" title="Star codebase-memory-mcp on GitHub" aria-label="Star this project on GitHub">★ Star on GitHub</a>
- </span>
- </div>
-</nav>
-
-<main class="container">
- <header class="hero">
- <h1>codebase-memory-mcp</h1>
- <p class="by-line">by DeusData</p>
- <p class="tagline">
- The fastest, most efficient code intelligence engine for AI coding agents. It indexes any
- repository into a persistent knowledge graph — full-indexing an average repo in seconds and the
- Linux kernel in 3 minutes — so your agent answers structural questions with ~120x fewer tokens.
- Tree-sitter parsing across 162 languages, Hybrid LSP type resolution, native executable with verified assets.
- </p>
- <div>
- <div class="stat"><div class="number">~120x</div><div class="label">fewer tokens</div></div>
- <div class="stat"><div class="number">158</div><div class="label">languages</div></div>
- <div class="stat"><div class="number">3 min</div><div class="label">Linux kernel index</div></div>
- <div class="stat"><div class="number">44</div><div class="label">client surfaces</div></div>
+<a class="skip" href="#main">Skip to content</a>
+<header class="site-header">
+ <nav class="container nav" aria-label="Main navigation">
+ <a class="brand" href="#main" aria-label="Codebase Memory home">
+ <svg viewBox="0 0 32 32" aria-hidden="true" fill="none"><path d="M8 8L25 15L11 25Z" stroke="currentColor" stroke-width="1.5"/><g fill="currentColor"><circle cx="8" cy="8" r="3"/><circle cx="25" cy="15" r="3"/><circle cx="11" cy="25" r="3"/></g></svg>
+ Codebase Memory
+ </a>
+ <div class="nav-links">
+ <a class="desktop-link" href="#features">Capabilities</a>
+ <a class="desktop-link" href="#lens">CBM Lens</a>
+ <a class="desktop-link" href="#smart-ci">Smart CI</a>
+ <a href="https://github.com/DeusData/codebase-memory-mcp">GitHub ↗</a>
+ <a class="nav-install" href="#install">Get started</a>
</div>
- <div class="cta-buttons">
- <a href="https://github.com/DeusData/codebase-memory-mcp" class="cta-primary">View on GitHub</a>
- <a href="https://github.com/DeusData/codebase-memory-mcp/releases/latest" class="cta-secondary">Download latest release</a>
+ </nav>
+</header>
+<main id="main" class="container">
+ <section class="hero" id="what-is-it">
+ <div class="hero-top">
+ <div>
+ <p class="eyebrow">Local code intelligence · Open source</p>
+ <h1>Understand the<br><span>whole repository.</span></h1>
+ <p class="hero-intro">Your code, documentation and infrastructure, connected in one persistent graph. Give your agent structural context. Follow the evidence yourself in CBM Lens.</p>
+ <div class="actions">
+ <a class="button primary" href="#install">Install Codebase Memory <span aria-hidden="true">↗</span></a>
+ <a class="button" href="#lens">Explore CBM Lens <span aria-hidden="true">↓</span></a>
+ </div>
+ <p class="hero-note">macOS · Linux · Windows &nbsp;/&nbsp; Native C · MIT licensed</p>
+ </div>
+ <div class="hero-aside">
+ <strong>For your agent</strong><p>Precise graph queries, source evidence and coverage checks through MCP.</p>
+ <strong>For you</strong><p>Source navigation, architecture maps and a visible path from question to code.</p>
+ </div>
</div>
- </header>
-
- <div class="screenshot">
- <img src="graph-ui-screenshot.png" width="1538" height="932" loading="lazy" decoding="async"
- alt="3D knowledge-graph visualization of the codebase-memory-mcp graph showing thousands of nodes and edges">
- <p class="caption">Built-in 3D graph visualization (UI variant) — explore your knowledge graph at <code>localhost:9749</code>.</p>
- </div>
-
- <aside class="research" aria-label="Research">
- <a class="arxiv-badge" href="https://arxiv.org/abs/2603.27277" rel="noopener">arXiv:2603.27277</a>
- <p>
- <span class="label">Research preprint.</span>
- The design and benchmarks are described in the preprint
- <a href="https://arxiv.org/abs/2603.27277"><em>Codebase-Memory: Tree-Sitter-Based Knowledge Graphs
- for LLM Code Exploration via MCP</em></a>. Evaluated across 31 real-world repositories:
- <strong>83% answer quality, 10× fewer tokens, and 2.1× fewer tool calls</strong> versus
- file-by-file exploration.
- </p>
- </aside>
-
- <section id="what-is-it">
- <h2>What is codebase-memory-mcp?</h2>
- <p class="lead">
- codebase-memory-mcp is an open-source <a href="https://modelcontextprotocol.io/">Model Context
- Protocol (MCP)</a> server that indexes a codebase into a persistent knowledge graph of functions,
- classes, call chains, HTTP routes, and cross-service links. Instead of reading files one at a time,
- an AI coding agent queries the graph — answering structural questions with roughly 120x fewer
- tokens. It parses 162 languages and ships as a native executable with authenticated release-owned assets;
- the native install needs no language runtime.
- </p>
- <p class="muted">
- It is a structural-analysis backend, not a chatbot: there is no embedded LLM and no API key. Your
- MCP client (Claude Code, or any MCP-compatible agent) is the intelligence layer; codebase-memory-mcp
- builds and serves the graph. All processing happens locally — your code never leaves your machine.
- </p>
- </section>
-
- <section id="problem">
- <h2>Why do AI agents waste tokens exploring code?</h2>
- <p class="lead">
- AI coding agents explore codebases by reading files one at a time. Every structural question
- triggers a cascade of grep → read file → grep again → read more files. The cost compounds fast.
- </p>
- <p style="margin-bottom: 16px;">
- Across five structural questions about a real codebase, file-by-file search consumed
- <strong style="color: var(--red);">~412,000 tokens</strong>; the same questions answered from the
- knowledge graph took <strong style="color: var(--green);">~3,400 tokens</strong> — a ~120x reduction.
- </p>
- <p class="muted">
- The win is not about fitting the context window. It is cost (at $3–15 per million tokens, exploration
- adds up), latency (sub-millisecond graph queries versus seconds of file reading), and accuracy
- (less noise means better answers and no "lost in the middle" problem).
- </p>
- <p><cite>Source: project benchmark, 5 structural queries — see the
- <a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md">full benchmark report</a>.</cite></p>
- </section>
-
- <section id="install">
- <h2>How do I install codebase-memory-mcp?</h2>
- <p class="lead">
- Install with a single command, then tell your agent to index the project. The native runtime set contains
- an executable with verified assets for macOS, Linux, and Windows — no Docker, language runtime, or API key.
- </p>
- <div class="install-block">
- <span class="comment"># 1. One-line install (macOS / Linux). Add --ui for the 3D graph UI.</span><br>
- <span class="cmd">curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash</span><br><br>
- <span class="comment"># 2. The installer configures detected clients; explicit flags cover conditional clients.</span><br><br>
- <span class="comment"># 3. Restart your agent, then say:</span><br>
- <span class="cmd">"Index this project"</span>
+ <figure class="product-shot">
+ <div class="shot-bar"><span class="live">CBM LENS BETA</span><span class="shot-path">codebase-memory-mcp / architecture</span><span>LOCAL WORKSPACE</span></div>
+ <a href="images/lens-architecture.png" aria-label="View the full CBM Lens architecture screenshot"><img src="images/lens-architecture.png" alt="CBM Lens architecture map showing the source folders of codebase-memory-mcp" fetchpriority="high"></a>
+ <figcaption>CBM Lens, exploring this repository. Real product captures from October 2026. <a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/images/README.md">Capture details ↗</a></figcaption>
+ </figure>
+ <div class="facts" aria-label="Project at a glance">
+ <div><strong>One connected graph</strong><span>Source, docs and infrastructure</span></div>
+ <div><strong>17 MCP tools</strong><span>Plus a CLI and CBM Lens</span></div>
+ <div><strong>45 client surfaces</strong><span>Automatic or conditional setup</span></div>
+ <div><strong>Local processing</strong><span>Your index stays on your machine</span></div>
</div>
- <p class="muted">
- One command configures 45 automatic/conditional client surfaces. <strong>Detected automatically (39):</strong>
- Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor,
- Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code,
- GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI,
- GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE,
- CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp).
- </p>
- <p class="muted">
- <strong>Conditional or explicit (6):</strong> Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE,
- and Sourcegraph Cody. <strong>Manual, UI, cloud, or repository-managed (not counted):</strong> Qodo,
- Warp MCP, JetBrains AI/ACP, GitHub Copilot coding agent, Jules, CodeRabbit, Replit, BLACKBOX AI,
- Plandex, and SWE-agent. Warp is counted above for its detected skill installation; its MCP connection
- remains manual. Windows users run <code>install.ps1</code>. Also available via <code>npm</code>,
- <code>pip</code>, Homebrew, Scoop, AUR, and <code>go install</code>.
- </p>
- <p class="muted">
- Lifecycle installation follows documented context contracts: Qoder uses <code>SessionStart</code>,
- <code>SubagentStart</code>, and post-<code>Read</code> coverage, including its documented Windows
- PowerShell executor. Kimi uses <code>UserPromptSubmit</code>;
- on macOS/Linux, GitLab Duo gets a fail-open user <code>SessionStart</code>, while Devin gets
- <code>UserPromptSubmit</code>, <code>PostCompaction</code>, and a deduplicated <code>SessionStart</code>
- when Claude does not already provide it. GitLab Duo, Devin, and Factory hooks are withheld on
- Windows where no deterministic shell/executor contract is documented. Cline's auto-activating file hooks
- are withheld because their context output is not reliably consumed; CodeBuddy's beta hooks are not
- auto-installed; Junie's EAP
- <code>SessionStart</code> output is documented as ignored; and Cursor context hooks are withheld because
- the documented events cannot safely provide race-free MCP context to read-only subagents.
- </p>
- <p class="muted">
- Documented custom-agent formats receive three exact-owned evidence tiers: Scout for narrow provisional
- discovery, Verify as the task-directed default, and Auditor for bounded, paginated, current-generation
- verification. Every direct tier calls <code>check_index_coverage</code> for cited paths and relevant scopes,
- then reads flagged ranges or skipped files directly. Kiro and Junie use positive-allowlist
- <code>--tool-profile scout</code> and <code>--tool-profile analysis</code> server surfaces;
- Junie selects dedicated named aliases because its subagent schema filters by server.
- Qoder combines named-server selection with exact tier-specific MCP tool IDs. Factory uses
- exact registered tool IDs without its additive whole-server <code>mcpServers</code> field.
- A foreign Junie alias is preserved and causes the installed profiles to fail closed to parent handoff.
- Cursor, Rovo, Augment, Pochi, and Cline use explicit
- parent handoff where direct child MCP is unavailable or unsafe; Pochi is limited to <code>readFile</code>.
- Neither IBM Bob surface receives an invented hook or custom agent. Amazon Q Developer
- IDE defaults to <code>~/.aws/amazonq/default.json</code> while preserving either existing documented
- alternative.
- </p>
- </section>
-
- <section id="hybrid-lsp">
- <h2>What is Hybrid LSP?</h2>
- <p class="lead">
- Hybrid LSP is semantic type resolution beyond tree-sitter. Tree-sitter alone produces a syntactic
- AST — it handles naming, structure, and call sites, but it cannot tell that
- <code>user.profile.display_name()</code> resolves to <code>Profile.display_name</code> declared
- three modules away, because it does not track imports, generics, inheritance, or stdlib types.
- </p>
- <p style="margin-bottom: 16px;">
- codebase-memory-mcp ships a <strong>lightweight C implementation of language type-resolution
- algorithms, structurally inspired by and compatible with major language servers</strong> —
- tsserver/typescript-go, pyright, gopls, Roslyn, Eclipse JDT, and rust-analyzer —
- embedded directly into the native executable. There is no language-server process, no
- per-project setup, and no API key. This layer runs alongside tree-sitter on every parse and refines
- <code>CALLS</code>, <code>USAGE</code>, and <code>RESOLVED_CALLS</code> edges with type information,
- so the graph mirrors what an IDE "Go to Definition" would resolve.
- </p>
- <h3>Languages with full Hybrid LSP</h3>
- <table class="lsp-table">
- <thead><tr><th>Language</th><th>What it resolves</th></tr></thead>
- <tbody>
- <tr><td>Python</td><td>Imports and dotted submodule walks, dataclasses, <code>Self</code> return types, generics, <code>@property</code>, <code>match/case</code> patterns, SQLAlchemy 2.0 <code>Mapped[T]</code>, Pydantic models, <code>typing</code> annotations, async/await, isinstance/walrus narrowing, and common stdlib.</td></tr>
- <tr><td>TypeScript / JavaScript / JSX / TSX</td><td>Generics, JSX component dispatch, JSDoc inference for plain JS, <code>.d.ts</code> declarations, module re-exports, and method chaining via return-type propagation across a shared cross-file registry.</td></tr>
- <tr><td>PHP</td><td>Namespaces, traits, late-static-binding, PHPDoc inference, parameter binding, and return-type inference.</td></tr>
- <tr><td>C#</td><td>Global usings, file-scoped namespaces, records (incl. C# 12 primary constructors), LINQ method syntax, <code>async Task&lt;T&gt;</code>/<code>ValueTask&lt;T&gt;</code> unwrap, generic methods, <code>var</code> inference, and common BCL stdlib.</td></tr>
- <tr><td>Go</td><td>Pre-built per-package cross-file registry, generics, embedded structs, interface satisfaction, and package-aware import resolution.</td></tr>
- <tr><td>C / C++</td><td>Shared cross-language registry: macros, <code>typedef</code> chains, and header-vs-source linking on the C side; templates, namespaces, <code>auto</code> inference, and class-hierarchy method resolution on the C++ side.</td></tr>
- <tr><td>Java <em>(new in v0.8.0)</em></td><td>Imports (single-type, on-demand, static), class hierarchies with <code>this</code>/<code>super</code> dispatch, generics, annotations, overload matching by arity and parameter types, lambdas and method references bound to functional interfaces, and common JDK stdlib.</td></tr>
- <tr><td>Kotlin <em>(new in v0.8.0)</em></td><td>Imports and same-package resolution, classes / objects / companion objects, extension functions, data classes, nullable-type unwrapping, scope functions (<code>let</code>/<code>apply</code>/<code>run</code>/<code>also</code>/<code>with</code>), infix calls, and common stdlib.</td></tr>
- <tr><td>Rust <em>(new in v0.8.0)</em></td><td><code>use</code> declarations and module paths, <code>impl</code> blocks and trait methods, struct fields, generics with trait bounds, operator-trait desugaring, derive-macro method synthesis, UFCS static paths, and common std prelude.</td></tr>
- </tbody>
- </table>
- <p class="muted">
- The two-layer pipeline runs a fast syntactic tree-sitter pass for every one of the 162 languages,
- then a type-aware Hybrid LSP pass on top for the families above. Languages without a Hybrid LSP pass
- yet fall back to textual resolution, so you always get an answer.
- </p>
</section>
- <section id="semantic-search">
- <h2>Can it do semantic and natural-language code search?</h2>
- <p class="lead">
- Yes. Beyond structural and full-text search, codebase-memory-mcp performs <strong>semantic
- vector search</strong> across the whole graph — so you can find code by meaning, not just by
- name. A search for <code>send</code> surfaces functions named <code>publish</code>,
- <code>emit</code>, or <code>dispatch</code>.
- </p>
- <p style="margin-bottom: 16px;">
- It is powered by <strong>nomic-embed-code embeddings compiled directly into the binary</strong>
- (768-dimensional, int8). There is no API key, no Ollama, and no Docker — the embeddings run
- on-device, so semantic search stays 100% local like everything else. Results combine
- <strong>11 signals</strong> (TF-IDF, API/type/decorator signatures, AST profiles, data flow,
- Halstead-lite complexity, MinHash, module proximity, and graph diffusion) into one relevance score.
- </p>
- <h3>Meaning-aware edges in the graph</h3>
- <p style="margin-bottom: 16px;">
- The indexer also writes two kinds of meaning-aware edges, queryable like any other relationship:
- </p>
- <table>
- <thead><tr><th>Edge</th><th>What it captures</th></tr></thead>
- <tbody>
- <tr><td><code>SEMANTICALLY_RELATED</code></td><td>Conceptually similar functions whose names and tokens differ — vocabulary-mismatch matches, scored ≥ 0.80, within the same language.</td></tr>
- <tr><td><code>SIMILAR_TO</code></td><td>Near-duplicate and copy-pasted code, detected with MinHash + LSH and Jaccard scoring — ideal for finding clones and refactor candidates.</td></tr>
- </tbody>
- </table>
- <div class="install-block" style="margin-top:16px;">
- <span class="comment"># Find code by meaning, not by name — embeddings run locally, no API key.</span><br>
- <span class="cmd">search_graph(semantic_query=["retry", "backoff", "exponential"])</span>
+ <section class="section" id="problem">
+ <div class="section-head">
+ <div><p class="eyebrow">Beyond file search</p><h2>Find the relationship.<br>Then read the evidence.</h2></div>
+ <p>A function rarely tells the whole story. Follow its callers, find the decision behind it, and trace the infrastructure that runs it.</p>
</div>
- <p class="muted">
- Semantic and similarity edges are computed in <code>full</code> and <code>moderate</code> index
- modes; <code>fast</code> mode skips them for the lowest-latency indexing.
- </p>
+ <div class="connection-grid">
+ <article class="connection">
+ <span class="number">01 / CODE</span><h3>What calls this?</h3>
+ <p>Explore symbols, call paths, types, dependencies and routes. Move across files, services and indexed repositories.</p>
+ <ul><li>Structural, full-text and local semantic search</li><li>Hybrid LSP type resolution for supported languages</li><li>HTTP, gRPC, GraphQL, tRPC and async links</li></ul>
+ <a class="source-link" href="#features">Explore code intelligence →</a>
+ </article>
+ <article class="connection" id="documentation">
+ <span class="number">02 / DOCUMENTATION</span><h3>Why does it work this way?</h3>
+ <p>Bring documentation into the graph. Search sections, follow resolved code references, and keep architecture decisions close to their implementation.</p>
+ <ul><li>Markdown, reStructuredText and AsciiDoc sections</li><li>Searchable pages from PDFs with text layers</li><li>ADRs, supersession and supported doc comments</li></ul>
+ <a class="source-link" href="https://github.com/DeusData/codebase-memory-mcp#documentation-connected-to-code">Documentation support →</a>
+ </article>
+ <article class="connection" id="infrastructure">
+ <span class="number">03 / INFRASTRUCTURE</span><h3>What builds and deploys it?</h3>
+ <p>Connect supported infrastructure and configuration to source. Trace the path from a service to the program inside its container.</p>
+ <ul><li>Docker, Compose, Kubernetes, Helm and Kustomize</li><li>Terraform / OpenTofu, Terragrunt and Ansible</li><li>Shell, Make and supported CI steps</li></ul>
+ <a class="source-link" href="https://github.com/DeusData/codebase-memory-mcp#infrastructure-and-deployment">Infrastructure support →</a>
+ </article>
+ </div>
+ <div class="trace-strip" aria-label="Example of a resolvable deployment path">
+ <span class="trace-label">A deployment path</span><span>Service</span><span class="arrow" aria-hidden="true">→</span><span>Workload</span><span class="arrow" aria-hidden="true">→</span><span>Image</span><span class="arrow" aria-hidden="true">→</span><span>Dockerfile</span><span class="arrow" aria-hidden="true">→</span><span>Program</span>
+ </div>
+ <p class="fine">Relationships come from supported source forms. Dynamic values and unresolved references can leave gaps; PDF extraction requires a text layer and does not perform OCR.</p>
</section>
- <section id="benchmark">
- <h2>How much does the knowledge graph save?</h2>
- <p class="lead">
- Each common structural question costs hundreds of tokens against the graph versus tens of thousands
- via file-by-file search. Totals across five queries: ~3,400 vs ~412,000 tokens.
- </p>
- <table class="benchmark-table">
- <thead>
- <tr><th>Question type</th><th>Graph</th><th>File-by-file</th><th>Savings</th></tr>
- </thead>
- <tbody>
- <tr><td>Find function by pattern</td><td>~200</td><td>~45,000</td><td class="win">225x</td></tr>
- <tr><td>Trace call chain (depth 3)</td><td>~800</td><td>~120,000</td><td class="win">150x</td></tr>
- <tr><td>Dead code detection</td><td>~500</td><td>~85,000</td><td class="win">170x</td></tr>
- <tr><td>List all routes</td><td>~400</td><td>~62,000</td><td class="win">155x</td></tr>
- <tr><td>Architecture overview</td><td>~1,500</td><td>~100,000</td><td class="win">67x</td></tr>
- <tr style="font-weight: 700;"><td>Total</td><td>~3,400</td><td>~412,000</td><td class="win">~121x</td></tr>
- </tbody>
- </table>
- <p class="muted" style="font-size: 0.9rem;">
- A separate evaluation across 31 real-world repositories, described in the preprint, reported 83% answer quality,
- 10x fewer tokens, and 2.1x fewer tool calls versus file-by-file exploration.
- </p>
- <p><cite>Source: <a href="https://arxiv.org/abs/2603.27277">“Codebase-Memory: Tree-Sitter-Based Knowledge
- Graphs for LLM Code Exploration via MCP”</a>, arXiv:2603.27277 — and the
- <a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md">project benchmark report</a>.</cite></p>
+ <section class="section" id="lens">
+ <div class="section-head">
+ <div><p class="eyebrow">CBM Lens Beta</p><h2>A workspace for<br>understanding your code.</h2></div>
+ <p>Included in standard native releases. Open the local browser interface and move from the shape of a system to the source behind a symbol.</p>
+ </div>
+ <div class="lens-grid">
+ <figure><a href="images/lens-explore.jpg" aria-label="View the full CBM Lens source navigation screenshot"><img src="images/lens-explore.jpg" alt="Lens source reader beside the file impact summary and graph dependencies for limits.c" loading="lazy"></a><figcaption>Source navigation with indexed relationships and impact context.</figcaption></figure>
+ <div class="lens-copy">
+ <div><h3>Read code in context</h3><p>Browse files and symbols, inspect callers and dependencies, and keep the relevant source beside the graph.</p></div>
+ <div><h3>See the shape of the system</h3><p>Explore architecture, system structure and the Galaxy graph. Inspect coverage diagnostics and architecture decisions from the same workspace.</p></div>
+ </div>
+ </div>
+ <div class="gallery">
+ <figure><a href="images/lens-galaxy.jpg" aria-label="View the full Lens Galaxy screenshot"><img src="images/lens-galaxy.jpg" alt="CBM Lens Galaxy graph for exploring symbols and relationships" loading="lazy"></a><figcaption><strong>Follow the connections</strong>Search and expand the Galaxy graph.</figcaption></figure>
+ <figure><a href="images/lens-system-structure.png" aria-label="View the full Lens system structure screenshot"><img src="images/lens-system-structure.png" alt="CBM Lens system structure showing source groups and their dependencies" loading="lazy"></a><figcaption><strong>Inspect system structure</strong>See source groups and dependencies.</figcaption></figure>
+ <figure><a href="images/lens-chat.png" aria-label="View the full Lens local chat screenshot"><img src="images/lens-chat.png" alt="CBM Lens optional local chat explaining selected source using indexed facts" loading="lazy"></a><figcaption><strong>Ask about selected code</strong>Optional browser AI, with on-device inference.</figcaption></figure>
+ </div>
+ <p class="fine">Lens is served on loopback. Browser AI downloads its optional model after you enable it. Its explanations should be checked against the displayed source.</p>
+ <a class="source-link" href="https://github.com/DeusData/codebase-memory-mcp#cbm-lens-beta-code-visualization-and-source-navigation">Read the Lens guide and watch the walkthroughs →</a>
</section>
- <section id="performance">
- <h2>How fast is it?</h2>
- <p class="lead">
- Indexing is RAM-first (LZ4 compression, in-memory SQLite, single dump at end) and memory is released
- to the OS afterward. Queries run in under a millisecond.
- </p>
- <table>
- <thead><tr><th>Operation</th><th>Time</th><th>Notes</th></tr></thead>
- <tbody>
- <tr><td>Linux kernel full index</td><td class="win">3 min</td><td>28M LOC, 75K files → 4.81M nodes, 7.72M edges</td></tr>
- <tr><td>Django full index</td><td class="win">~6 s</td><td>49K nodes, 196K edges</td></tr>
- <tr><td>Cypher query</td><td class="win">&lt;1 ms</td><td>Relationship traversal</td></tr>
- <tr><td>Name search (regex)</td><td class="win">&lt;10 ms</td><td>SQL LIKE pre-filtering</td></tr>
- <tr><td>Trace call path (depth 5)</td><td class="win">&lt;10 ms</td><td>BFS traversal</td></tr>
- </tbody>
- </table>
- <p><cite>Source: project Performance benchmarks, measured on Apple M3 Pro.</cite></p>
+ <section class="section" id="features">
+ <div class="section-head">
+ <div><p class="eyebrow">Code intelligence</p><h2>Ask better questions<br>of your repository.</h2></div>
+ <p>Use the same persistent graph through your coding agent, the CLI or Lens. Open source evidence whenever a result needs verification.</p>
+ </div>
+ <article class="feature-row" id="semantic-search"><h3>Find the right starting point</h3><div><p>Search by symbol, structure, text or meaning. Combine regex and graph filters, BM25 full-text search, and local semantic search to find relevant code even when the wording differs.</p><div class="tags"><span class="tag">search_graph</span><span class="tag">search_code</span><span class="tag">get_file_outline</span></div></div></article>
+ <article class="feature-row" id="hybrid-lsp"><h3>Follow actual relationships</h3><div><p>Tree-sitter parsing and Hybrid LSP resolution build call and dependency relationships for supported languages. Trace callers, callees, data flow and supported cross-service links; query more complex patterns with Cypher.</p><p>Language and framework coverage varies. <a href="https://github.com/DeusData/codebase-memory-mcp#language-support">Check the support matrix →</a></p></div></article>
+ <article class="feature-row"><h3>Understand change</h3><div><p>Map a diff to affected symbols, investigate the blast radius, compare graph snapshots and inspect related tests. Near-clone and semantic relationships help surface related implementations worth reviewing.</p><div class="tags"><span class="tag">detect_changes</span><span class="tag">compare_graphs</span><span class="tag">SIMILAR_TO</span></div></div></article>
+ <article class="feature-row"><h3>Connect the wider system</h3><div><p>Link multiple repositories in the same store. Explore service relationships across HTTP, gRPC, GraphQL, tRPC and supported async patterns, or ingest runtime traces to add observed relationships.</p><div class="tags"><span class="tag">Cross-repo intelligence</span><span class="tag">ingest_traces</span><span class="tag">get_architecture</span></div></div></article>
+ <article class="feature-row"><h3>Know what the index knows</h3><div><p>Inspect index status and recorded coverage before making a claim. Coverage diagnostics identify skipped, partial or stale evidence so you can read the relevant source directly. Preserve architecture decisions with ADR management.</p><div class="tags"><span class="tag">check_index_coverage</span><span class="tag">index_status</span><span class="tag">manage_adr</span></div></div></article>
+ <details><summary>Explore all 17 MCP tools</summary><div class="tool-list"><code>index_repository</code><code>search_graph</code><code>query_graph</code><code>trace_path</code><code>get_code_snippet</code><code>get_file_outline</code><code>get_graph_schema</code><code>compare_graphs</code><code>get_architecture</code><code>search_code</code><code>list_projects</code><code>delete_project</code><code>index_status</code><code>check_index_coverage</code><code>detect_changes</code><code>manage_adr</code><code>ingest_traces</code></div><p><a href="https://github.com/DeusData/codebase-memory-mcp#mcp-tools">Tool reference, inputs and examples →</a></p></details>
</section>
- <section id="features">
- <h2>Features</h2>
- <div class="features">
- <div class="feature">
- <h3>162 languages</h3>
- <p>Python, Go, JS, TS, TSX, Rust, Java, C++, C#, C, PHP, Ruby, Kotlin, Scala, Zig, Elixir, Haskell, OCaml, Swift, Dart, Lean 4, and many more via vendored tree-sitter grammars compiled into the binary.</p>
- </div>
- <div class="feature">
- <h3>Hybrid LSP type resolution</h3>
- <p>Language-server-grade type inference for Python, TS/JS, PHP, C#, Go, C/C++, Java, Kotlin, and Rust — embedded in the binary, no server process or per-project setup.</p>
- </div>
- <div class="feature">
- <h3>Pure C, no language runtime</h3>
- <p>A native executable with authenticated release-owned assets for macOS, Linux, and Windows. The native install needs no Docker, language runtime, or API keys; fully static Linux builds are available in the <code>-portable</code> archives.</p>
- </div>
- <div class="feature">
- <h3>Call-graph tracing</h3>
- <p>Trace callers and callees across files and packages with import-aware, type-inferred resolution. BFS traversal up to depth 5.</p>
- </div>
- <div class="feature">
- <h3>Dead-code detection</h3>
- <p>Find functions with zero callers, with smart filtering that excludes entry points like route handlers, <code>main()</code>, and framework decorators.</p>
- </div>
- <div class="feature">
- <h3>Cross-service linking</h3>
- <p>Matches REST routes to HTTP call sites across services with confidence scoring — and detects gRPC, GraphQL, and tRPC services plus pub/sub channels (<code>EMITS</code>/<code>LISTENS_ON</code> for Socket.IO, EventEmitter, and message buses) and async queue dispatch.</p>
- </div>
- <div class="feature">
- <h3>Infrastructure-as-code indexing</h3>
- <p>Dockerfiles, Kubernetes manifests, and Kustomize overlays become graph nodes with cross-references to the resources they configure.</p>
- </div>
- <div class="feature">
- <h3>Auto-sync</h3>
- <p>A background watcher detects changes in the project your MCP session is working in and re-indexes it incrementally. No manual reindex after editing files there.</p>
- </div>
- <div class="feature">
- <h3>Team-shared graph artifact</h3>
- <p>Commit one zstd-compressed snapshot (<code>.codebase-memory/graph.db.zst</code>); teammates bootstrap from it and skip the full reindex.</p>
- </div>
- <div class="feature">
- <h3>3D graph visualization</h3>
- <p>The optional UI variant adds one verified, content-addressed frontend pack and serves an interactive 3D graph at <code>localhost:9749</code> to explore nodes, edges, and clusters visually.</p>
- </div>
- <div class="feature">
- <h3>17 MCP tools</h3>
- <p><code>search_graph</code>, <code>trace_path</code>, <code>detect_changes</code>, <code>query_graph</code> (Cypher), <code>get_architecture</code>, <code>get_code_snippet</code>, <code>check_index_coverage</code>, <code>manage_adr</code>, and 9 more.</p>
- </div>
- <div class="feature">
- <h3>Cypher graph queries</h3>
- <p>Run read-only Cypher-style queries against the graph for multi-hop patterns that structured search can't express.</p>
- </div>
- <div class="feature">
- <h3>Semantic code search</h3>
- <p>Find code by meaning, not just name, via <code>semantic_query</code> vector search — powered by nomic-embed-code embeddings baked into the binary. No API key, fully local.</p>
- </div>
- <div class="feature">
- <h3>Clone &amp; similarity detection</h3>
- <p><code>SIMILAR_TO</code> edges (MinHash + LSH) surface near-duplicate code; <code>SEMANTICALLY_RELATED</code> edges link conceptually similar functions across the graph.</p>
- </div>
- <div class="feature">
- <h3>Cross-repo intelligence</h3>
- <p>Index multiple repositories in one store and link them with <code>CROSS_*</code> edges. A multi-galaxy 3D layout and cross-repo architecture summary span the whole fleet.</p>
- </div>
- <div class="feature">
- <h3>Data-flow tracing</h3>
- <p><code>DATA_FLOWS</code> edges follow values from argument to parameter, with field-access chains — trace how data moves, not just who calls whom.</p>
- </div>
- <div class="feature">
- <h3>Change-impact analysis</h3>
- <p><code>detect_changes</code> maps an uncommitted git diff to affected symbols and their blast radius, with risk classification — see what a change touches before you ship it.</p>
- </div>
- <div class="feature">
- <h3>Architecture Decision Records</h3>
- <p><code>manage_adr</code> persists architectural decisions alongside the graph, so design rationale survives across sessions and teammates.</p>
+ <section class="section" id="smart-ci">
+ <div class="split">
+ <div><p class="eyebrow">Smart CI <span class="label">Experimental</span></p><h2>Turn change impact<br>into test selection.</h2><p>Combine static reachability, changed tests and admitted per-test coverage to explain which tests a change reaches. Use the result to focus supported CI runs.</p><p>Job selection uses repository-specific path rules. Test narrowing currently supports C/C++ with supported <code>TEST</code>/<code>SUITE</code>-style harnesses or declared equivalents.</p><p class="fine">Start in shadow mode and validate your harness before enabling gating. This repository narrows its Linux x86_64 PR unit-test leg; release and dry-run workflows retain full execution.</p><a class="source-link" href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/SMART_CI.md">Read the Smart CI setup guide →</a></div>
+ <div class="ci-panel">
+ <div class="ci-title">FROM CHANGE TO EXPLAINED SELECTION</div>
+ <div class="ci-step"><span class="number">01</span><div><strong>Establish a baseline</strong><p>Publish the graph and compatible per-test coverage with <code>test-impact publish</code>.</p></div></div>
+ <div class="ci-step"><span class="number">02</span><div><strong>Trace the change</strong><p>Combine changed tests, static relationships and admitted coverage.</p></div></div>
+ <div class="ci-step"><span class="number">03</span><div><strong>Select with reasons</strong><p><code>test-impact select</code> explains its selection for a runner that accepts named tests or suites.</p></div></div>
+ <div class="ci-step fallback"><span class="number">↳</span><div><strong>Broaden when evidence is insufficient</strong><p>Missing, stale or incomplete evidence broadens the selection or returns <code>run_all</code>. Static reachability alone never omits a suite.</p></div></div>
</div>
</div>
</section>
- <section id="releases">
- <h2>What are the recent releases?</h2>
- <p class="lead">
- The latest release notes are loaded live from GitHub. Each entry links to its full changelog.
- </p>
- <div id="releases-list">
- <p class="skeleton">Loading recent releases from GitHub…</p>
+ <section class="section" id="integrations">
+ <div class="section-head"><div><p class="eyebrow">Agent setup</p><h2>Context that fits<br>your coding workflow.</h2></div><p>The installer configures 45 automatic/conditional client surfaces. MCP connections, instructions, skills, profiles and hooks are installed according to each client's supported capabilities.</p></div>
+ <div class="integration-flow">
+ <div class="integration-step"><span class="number">01 / CONNECT</span><strong>Set up your clients</strong><p>Configure supported integrations for clients such as Claude Code, Codex CLI, Gemini CLI, Cursor, Zed and OpenCode.</p></div>
+ <div class="integration-step"><span class="number">02 / GUIDE</span><strong>Give agents a working method</strong><p>Skills and instructions guide graph queries, coverage checks and source verification. Supported custom-agent formats get Scout, Verify and Auditor profiles.</p></div>
+ <div class="integration-step"><span class="number">03 / MAINTAIN CONTEXT</span><strong>Use supported hooks</strong><p>Client-specific lifecycle and read/search hooks help surface relevant graph context. Hook and subagent capabilities differ by client and platform.</p></div>
</div>
- <p style="margin-top: 16px;">
- <a href="https://github.com/DeusData/codebase-memory-mcp/releases">View all releases on GitHub →</a>
- </p>
+ <details><summary>See the supported clients and integration boundaries</summary>
+ <p><strong>Detected automatically (39):</strong> Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp).</p>
+ <p><strong>Conditional or explicit (6):</strong> Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody.</p>
+ <p>These are client surfaces, not a promise of identical MCP, hook or subagent support. For example, Pi receives instructions and a skill; Warp's detected skill installation is counted while its MCP connection remains manual. Other manual, UI, cloud and repository-managed integrations are documented separately.</p>
+ <p><a href="https://github.com/DeusData/codebase-memory-mcp#agent-setup-skills-profiles-and-hooks">Review the client matrix and setup details →</a></p>
+ </details>
</section>
- <section id="faq" class="faq">
- <h2>Frequently asked questions</h2>
+ <section class="section" id="install">
+ <div class="section-head"><div><p class="eyebrow">Get started</p><h2>Install. Index. Explore.</h2></div><p>Standard native releases include CBM Lens. The native runtime needs no Docker or language runtime; the core indexer and graph queries need no API key.</p></div>
+ <div class="split">
+ <div><div class="terminal"><div class="terminal-head">TERMINAL · macOS / Linux</div><pre><code><span class="comment"># Install the native release and agent integrations</span>
+<span class="command">curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash</span>
- <h3>Does codebase-memory-mcp send my code anywhere?</h3>
- <p>No. All indexing and querying happen 100% locally. There is no embedded LLM and no API key. Release
- archives are signed and checksummed. Before testing, three behaviourally identical executable candidates
- (unstripped, debug-stripped, stripped) for every platform and link mode are submitted to VirusTotal; the selected candidate is packaged with its
- SHA-256 unchanged. Release notes link every measured result. Publication permits only the
- documented single-Microsoft <code>!ml</code> tolerance.</p>
+<span class="comment"># Restart your agent, then ask:</span>
+"Index this project"
- <h3>Does it support semantic or natural-language code search?</h3>
- <p>Yes. Alongside structural and full-text search, <code>search_graph</code>'s <code>semantic_query</code>
- parameter runs vector search over the whole graph, powered by nomic-embed-code embeddings compiled
- into the binary — so it finds <code>publish</code> when you search <code>send</code>. No API key, no
- Ollama, no Docker; the embeddings run on-device. The indexer also builds <code>SEMANTICALLY_RELATED</code>
- edges between similar functions and <code>SIMILAR_TO</code> edges for near-clone detection.</p>
-
- <h3>Do I need Docker or a runtime?</h3>
- <p>The native install needs no language runtime. It is a native executable with authenticated release-owned
- assets for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (arm64/amd64); npm, PyPI, and Go wrapper
- installations naturally use their package runtime.</p>
+<span class="comment"># Open CBM Lens in your browser</span>
+<span class="command">codebase-memory-mcp daemon start --open</span></code></pre></div><div class="install-links"><a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/install.sh">Inspect the installer ↗</a><a href="https://github.com/DeusData/codebase-memory-mcp#quick-start">Windows / PowerShell ↗</a><a href="https://github.com/DeusData/codebase-memory-mcp#installation">Other installation methods ↗</a></div></div>
+ <div class="install-copy"><h3>Your machine. Your index.</h3><p>Source analysis and graph storage run locally. Native releases contain the executable and authenticated release-owned assets, including the Lens frontend and agent integration templates.</p><p>Use native packages or the npm, PyPI and Go wrappers. Package wrappers use their respective runtimes. Nix and source builds also offer builds without the UI.</p><p>Choose the clients you want to configure, restart them after installation, then build your first index.</p><a class="button" href="https://github.com/DeusData/codebase-memory-mcp/releases/latest">Download the latest release <span aria-hidden="true">↗</span></a></div>
+ </div>
+ </section>
- <h3>How does it stay up to date as I edit code?</h3>
- <p>A background watcher detects file changes and re-indexes incrementally — typically a sub-millisecond
- no-op when nothing changed. You only run a manual index for the first build or after a large
- <code>git pull</code>.</p>
+ <section class="section" id="performance">
+ <div class="evidence" id="benchmark"><div><p class="eyebrow">Performance and research</p><h2>Useful context.<br>Measurable tradeoffs.</h2></div><div><p>Focused graph queries can reduce repeated file exploration. The result depends on the repository, the question, the agent and how much source verification the task needs.</p><p>Published benchmarks describe specific workloads, hardware and answer-quality tradeoffs. They are backend measurements, not a promise of a fixed saving or a benchmark of CBM Lens.</p><div class="evidence-links"><a href="https://github.com/DeusData/codebase-memory-mcp#performance">Results and limitations ↗</a><a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md">Benchmark methodology ↗</a><a href="https://arxiv.org/abs/2603.27277">Research paper ↗</a></div></div></div>
+ </section>
- <h3>Why is there no built-in LLM?</h3>
- <p>Other code-graph tools embed an LLM to translate natural language into graph queries, which means
- extra API keys and cost. With MCP, the agent you are already talking to is the query translator —
- codebase-memory-mcp just builds and serves the graph.</p>
+ <section class="section" id="faq">
+ <div class="faq"><p class="eyebrow">A few practical details</p><h2>Before you start.</h2>
+ <details><summary>Does Codebase Memory send my source code anywhere?</summary><p>The backend indexes source and stores and queries its graph locally. Your coding agent has its own data-handling settings. Lens can optionally download a browser model after you enable it, with inference on-device. Installers and update checks use the network to obtain releases and assets.</p></details>
+ <details><summary>How does the index stay current?</summary><p>Incremental indexing updates changed files. With auto-watch enabled, an eligible active MCP session can watch an already indexed project. Automatic first indexing is a separate opt-in setting. The local UI daemon is not a promise of a permanent background watcher.</p></details>
+ <details><summary>How much language coverage is available?</summary><p>Bundled tree-sitter grammars cover a broad range of languages and formats. Supported language families also have Hybrid LSP semantic resolution. Extraction depth, type resolution and framework relationships vary; the <a href="https://github.com/DeusData/codebase-memory-mcp#language-support">language support matrix</a> describes the details.</p></details>
+ <details><summary>Does Smart CI select tests for every indexed language?</summary><p>No. Test narrowing currently supports C/C++ family code with supported test-harness conventions or declared equivalents. It requires configuration, admitted coverage and a compatible runner. Missing or incompatible evidence broadens execution or returns <code>run_all</code>. See the <a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/SMART_CI.md">Smart CI guide</a>.</p></details>
+ <details><summary>How do I verify the release?</summary><p>Use the signed release artifacts and checksums, and review the release's verification information. The <a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/SECURITY.md">security policy</a> explains artifact verification, antivirus reports and vulnerability reporting.</p></details>
+ <details><summary>Is it free and open source?</summary><p>Yes. Codebase Memory is MIT licensed. Source, release binaries, detailed documentation and contribution guidelines are available on <a href="https://github.com/DeusData/codebase-memory-mcp">GitHub</a>.</p></details>
+ </div>
+ </section>
- <h3>Is it free and open source?</h3>
- <p>Yes. It is MIT licensed. The full source, signed release binaries, and checksums are on
- <a href="https://github.com/DeusData/codebase-memory-mcp">GitHub</a>.</p>
+ <section class="section" id="releases">
+ <div class="section-head"><div><p class="eyebrow">Project updates</p><h2>What's shipping.</h2></div><p>Recent releases from GitHub, with the implementation details and fixes behind each version.</p></div>
+ <div id="releases-list"><p class="skeleton">Loading recent releases from GitHub…</p></div>
+ <noscript><p><a href="https://github.com/DeusData/codebase-memory-mcp/releases">Read the release history on GitHub →</a></p></noscript>
+ <a class="source-link" href="https://github.com/DeusData/codebase-memory-mcp/releases">View all releases on GitHub →</a>
</section>
</main>
-
-<footer>
- <div class="container">
- <p>
- Open source, MIT licensed.
- <a href="https://github.com/DeusData/codebase-memory-mcp">GitHub</a> &middot;
- <a href="https://github.com/DeusData/codebase-memory-mcp/releases/latest">Releases</a> &middot;
- <a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md">Benchmarks</a> &middot;
- <a href="https://arxiv.org/abs/2603.27277">Paper</a>
- </p>
- </div>
-</footer>
+<footer><div class="container footer-inner"><div><a class="brand" href="#main">Codebase Memory</a><p>Local code intelligence. Open source, MIT licensed.</p></div><div class="footer-links"><a href="https://github.com/DeusData/codebase-memory-mcp">GitHub</a><a href="https://github.com/DeusData/codebase-memory-mcp#readme">Documentation</a><a href="https://github.com/DeusData/codebase-memory-mcp/blob/main/SECURITY.md">Security</a><a href="llms.txt">llms.txt</a></div></div></footer>
<script>
(function () {
@@ -919,6 +521,5 @@
});
})();
</script>
-
</body>
</html>
diff --git a/docs/llms.txt b/docs/llms.txt
index 0d0c5a49c..ba3c3dc25 100644
--- a/docs/llms.txt
+++ b/docs/llms.txt
@@ -1,26 +1,45 @@
# codebase-memory-mcp
-> An open-source Model Context Protocol (MCP) server that indexes a codebase into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. AI coding agents query the graph instead of reading files one by one, answering structural questions with roughly 120x fewer tokens (~3,400 vs ~412,000 across five structural queries). Parses 162 languages via vendored tree-sitter grammars, with Hybrid LSP semantic type resolution for Python, TypeScript/JavaScript, PHP, C#, Go, C/C++, Java, Kotlin, and Rust. It also generates semantic graph edges (SEMANTICALLY_RELATED for vocabulary-mismatch matches, SIMILAR_TO for near-clone detection) and supports semantic vector search via bundled nomic-embed-code embeddings compiled into the native executable — no API key, no Ollama, no Docker. Ships a native executable with an authenticated integration asset; the UI variant adds one content-addressed frontend pack. All processing is local — the embeddings run on-device; there is no embedded LLM and no API key.
-
-## Key facts
-
-- License: MIT, open source.
-- Languages: 158 (158 vendored tree-sitter grammars compiled into the binary).
-- Hybrid LSP type resolution: 9 language families (Python, TypeScript/JavaScript/JSX/TSX, PHP, C#, Go, C/C++, Java, Kotlin, Rust) — a lightweight C implementation of language type-resolution algorithms, structurally inspired by and compatible with major language servers including tsserver, pyright, gopls, Roslyn, Eclipse JDT, and rust-analyzer.
-- MCP tools: 15 (search_graph incl. semantic_query vector search, trace_path (alias: trace_call_path), check_index_coverage, query_graph (Cypher), detect_changes, get_architecture, get_code_snippet, manage_adr, and more).
-- Semantic search: natural-language code discovery via bundled nomic-embed-code embeddings (768-dim, compiled into the binary); 11-signal combined scoring; fully local, no API key.
-- Semantic & similarity edges: SEMANTICALLY_RELATED (vocabulary-mismatch matches) and SIMILAR_TO (MinHash + LSH near-clone / duplicate detection).
-- Cross-repo intelligence: CROSS_* edges link nodes across multiple repos indexed in one store; multi-galaxy 3D layout and cross-repo architecture summary.
-- Cross-service linking: HTTP route ↔ call-site matching, plus gRPC/GraphQL/tRPC detection and pub/sub channels (EMITS/LISTENS_ON for Socket.IO, EventEmitter, generic buses).
+> Local code intelligence for developers and AI agents. Connect code, documentation, configuration, and infrastructure in a persistent knowledge graph. Search for a feature, follow callers and dependencies, trace services and deployments, inspect change impact, and explore the evidence in CBM Lens. Access the same backend through MCP or the CLI. Indexing, graph queries, and semantic embeddings run locally without a hosted service or API key; Lens optionally downloads a browser model after opt-in for on-device code chat.
+
+## Capabilities
+
+- Code exploration: symbol and structural search, BM25 text search, semantic search, source snippets and file outlines, call paths, data flow, architecture summaries, hotspots, cycles, and coverage diagnostics. The server registers 17 MCP tools.
+- Semantic and similarity relationships: bundled embeddings support natural-language discovery; SEMANTICALLY_RELATED edges connect vocabulary-mismatch matches, and SIMILAR_TO edges expose near-clone candidates.
+- Languages and formats: vendored parsers cover source, documentation, and configuration formats. Hybrid LSP adds semantic type resolution for Python, TypeScript/JavaScript/JSX/TSX, PHP, C#, Go, C/C++, Java, Kotlin, Rust, and Perl. Support and resolution depth differ by language; use the README language matrix and check_index_coverage for the indexed project.
+- Documentation connected to code: Markdown, reStructuredText, and AsciiDoc sections; PDF text pages (no OCR); supported document and language doc-comment references to code; ADR metadata and supersession. Supported diagrams and OpenAPI descriptions contribute entities, with format-specific reference-resolution limits.
+- Infrastructure and deployment: Docker/Compose, Kubernetes, Helm, Kustomize, Terraform/OpenTofu, Terragrunt, Ansible, shell, Make, and supported CI relationships. Trace deployments, images, entrypoints, configuration keys, and environment-variable access back to source when inputs can be resolved statically.
+- Cross-service and cross-repository relationships: supported HTTP, asynchronous messaging, gRPC, GraphQL, and tRPC links. Cross-repo analysis explicitly links projects indexed in the same store; missing links do not prove that no runtime relationship exists.
+- Change impact: detect_changes maps diffs to affected symbols and investigates related tests with scope: "tests"; compare_graphs compares indexed snapshots.
+- Smart CI (experimental): repository-specific changed-file rules select CI jobs; test-impact select combines static reachability, changed tests, and admitted per-test coverage to select tests. Narrowing supports C/C++ family code with supported test-harness conventions and an explicitly configured runner. Missing or doubtful evidence broadens the selection or runs all tests. Other indexed languages are not automatically supported for test narrowing. test-impact publish creates the baseline graph-and-coverage bundle. Start in shadow mode; consult the guide for version requirements.
+- Architecture decisions and runtime evidence: manage_adr stores the project's decision record; ingest_traces adds separately collected observed call relationships alongside static analysis.
+- CBM Lens Beta: local browser interface with source exploration, Galaxy graph navigation, architecture and behavior views, ADR editing, index-coverage diagnostics, daemon/system information, and optional local code chat. Static graph animations are not live execution traces. Activity overlays are experimental source-build features, not a standard-release promise.
+- Agent integrations: 45 automatic or conditional client surfaces. Installation configures supported MCP entries, durable instructions, skills, Scout/Verify/Auditor profiles, and applicable session, compaction, search, and read hooks. Coverage and activation vary by client and platform. Hooks provide context without blocking or replacing the user's tool call; some clients require trust or use parent-agent handoff instead.
+- Persistent operation: a per-account daemon coordinates sessions and indexing. Existing indexes can stay synchronized during eligible active MCP sessions; initial auto-indexing is separately opt-in. Optional team graph artifacts share a baseline while each user keeps a local query database.
+- Distribution: native C backend, MIT license, standard native releases for macOS, Linux, and Windows include CBM Lens; Linux portable archives provide static builds. Nix and development source builds can omit the UI. Package-manager options and release verification are documented in the README.
+
+## Client coverage
+
- Supported agents: 45 automatic/conditional client surfaces (39 automatically detected + 6 conditional/explicit): Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Continue / cn, Visual Studio, TRAE, Roo Code, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob IDE, IBM Bob Shell, Pochi, Pi, Oh My Pi (omp), and Sourcegraph Cody.
-- Agent profiles: documented custom-agent formats receive Scout (fast/provisional), Verify (default/task-directed), and Auditor (bounded/full verification) definitions. Every direct tier checks exact path/scope coverage with check_index_coverage and falls back to source for flagged gaps; unsafe child-MCP formats use explicit parent handoff. Kiro and Junie use positive-allowlist Scout/Analysis server profiles (7/11 tools); Qoder combines named-server selection with exact tier-specific MCP tool IDs, while Factory uses exact registered IDs without additive whole-server exposure. Foreign Junie aliases are preserved and force parent handoff.
-- Performance: Linux kernel (28M LOC, 75K files) full index in 3 minutes → 4.81M nodes, 7.72M edges; Cypher queries in under 1ms.
-- Distribution: verified runtime set (native executable plus authenticated release-owned assets); fully static Linux builds are available in the `-portable` archives. Also available through npm, PyPI, Homebrew, Scoop, AUR, and `go install`.
+
+## Measurement and limits
+
+Published performance and token comparisons apply to specific workloads, hardware, and agent setups, not a universal percentage saving. The README Performance section preserves the historical comparison and research quality tradeoff. Check index generation, freshness, and exact path/scope coverage before relying on graph results, especially absence claims; read source when coverage is partial, skipped, excluded, stale, or unknown. Infrastructure relationships are static, and test-selection support is narrower than language-indexing support.
## Links
- Homepage: https://deusdata.github.io/codebase-memory-mcp/
-- Source code (GitHub): https://github.com/DeusData/codebase-memory-mcp
+- Source and feature reference: https://github.com/DeusData/codebase-memory-mcp
- Latest release: https://github.com/DeusData/codebase-memory-mcp/releases/latest
+- Quick start and installation: https://github.com/DeusData/codebase-memory-mcp#quick-start
+- Documentation indexing: https://github.com/DeusData/codebase-memory-mcp#documentation-connected-to-code
+- Infrastructure and deployment: https://github.com/DeusData/codebase-memory-mcp#infrastructure-and-deployment
+- CBM Lens: https://github.com/DeusData/codebase-memory-mcp#cbm-lens-beta-code-visualization-and-source-navigation
+- Agent integrations: https://github.com/DeusData/codebase-memory-mcp#multi-agent-support
+- Smart CI guide: https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/SMART_CI.md
+- Configuration: https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/CONFIGURATION.md
+- MCP tools: https://github.com/DeusData/codebase-memory-mcp#mcp-tools
+- Performance and research limits: https://github.com/DeusData/codebase-memory-mcp#performance
- Benchmark report: https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md
- Research paper: https://arxiv.org/abs/2603.27277
+- Security and release verification: https://github.com/DeusData/codebase-memory-mcp#security
diff --git a/pkg/npm/README.md b/pkg/npm/README.md
index 63dc88f0b..bce4d5217 100644
--- a/pkg/npm/README.md
+++ b/pkg/npm/README.md
@@ -5,9 +5,9 @@
[![License](https://img.shields.io/badge/license-MIT-green)](https://github.com/DeusData/codebase-memory-mcp/blob/main/LICENSE)
[![Platform](https://img.shields.io/badge/macOS_%7C_Linux_%7C_Windows-supported-lightgrey)](https://github.com/DeusData/codebase-memory-mcp/releases/latest)
-**The fastest and most efficient code intelligence engine for AI coding agents.** Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. This npm wrapper downloads, verifies, and caches the selected native runtime set: the executable, its authenticated integration asset, and—when requested—the content-addressed UI pack.
+**Local code intelligence for developers and AI agents.** CBM connects source code, documentation and infrastructure in a persistent knowledge graph. Explore through MCP, the CLI or CBM Lens to find code, trace dependencies and deployments, and understand what a change affects.
-High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across 162 languages — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 17 MCP tools. No hosted service or API key; this package requires Node.js to manage and launch the cached native runtime set. Plug and play across 45 automatic/conditional client surfaces.
+This npm wrapper downloads, verifies and caches the native executable, its authenticated integration asset and the content-addressed Lens frontend pack. Node.js manages installation and launch; the graph is processed locally without a hosted service or API key. The installer offers 45 client integration targets, with capabilities that vary by client.
## Installation
@@ -25,14 +25,16 @@ Then configure your coding agents:
codebase-memory-mcp install
```
-Restart your agent. Say **"Index this project"** — done.
+Restart your agent and ask it to **"Index this project"**. Use `codebase-memory-mcp daemon start --open` to open CBM Lens. Supported integrations also install graph instructions, skills, agent profiles and context hooks; consult the full client matrix for differences.
## Why codebase-memory-mcp
-- **Extreme indexing speed** — Linux kernel (28M LOC, 75K files) in 3 minutes. RAM-first pipeline with LZ4 compression and in-memory SQLite.
+- **Connected repository knowledge** — source symbols and calls, documentation sections and references, configuration, infrastructure and cross-service links.
- **Plug and play** — verified native runtime sets for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (arm64/amd64). No Docker or API keys; Node.js owns package download, cache repair, and launch.
-- **162 languages** — vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks.
-- **120x fewer tokens** — 5 structural queries: ~3,400 tokens vs ~412,000 via file-by-file search.
+- **Broad language and format support** — bundled parsers, with deeper semantic resolution for supported language families. See the [language reference](https://github.com/DeusData/codebase-memory-mcp#language-support) for coverage.
+- **Focused context** — retrieve symbols, relationships and bounded source excerpts instead of repeatedly reading whole files. Savings depend on the task and workflow.
+- **CBM Lens** — explore source, architecture, call paths, decisions and index coverage in a local browser workspace.
+- **Smart CI** — experimental change-aware test selection for supported C/C++ test runners, using graph relationships and admitted per-test coverage. Missing evidence broadens execution. See the [Smart CI guide](https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/SMART_CI.md).
- **45 supported automatic/conditional client surfaces** — `install` configures the appropriate MCP, durable-context, and documented hook surfaces without widening client permissions.
- **Detected automatically (39)** — Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, and Oh My Pi (omp).
- **Conditional or explicit (6)** — Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody. Bob IDE is touched only when `~/.bob/mcp.json` already exists.
@@ -68,30 +70,25 @@ Every MCP tool is also available directly from the command line:
```bash
codebase-memory-mcp cli index_repository '{"repo_path": "/path/to/repo"}'
-codebase-memory-mcp cli search_graph '{"name_pattern": ".*Handler.*", "label": "Function"}'
-codebase-memory-mcp cli trace_call_path '{"function_name": "main", "direction": "both"}'
-codebase-memory-mcp cli get_architecture '{}'
+codebase-memory-mcp cli list_projects '{}'
+# Replace PROJECT with the indexed project name returned above.
+codebase-memory-mcp cli search_graph '{"project":"PROJECT","name_pattern":".*Handler.*","label":"Function"}'
+codebase-memory-mcp cli trace_path '{"project":"PROJECT","function_name":"main","direction":"both"}'
+codebase-memory-mcp cli get_architecture '{"project":"PROJECT"}'
```
## MCP Tools
| Category | Tools |
|----------|-------|
-| **Indexing** | `index_repository`, `list_projects`, `delete_project`, `index_status` |
-| **Querying** | `search_graph`, `trace_call_path`, `detect_changes`, `query_graph` |
-| **Analysis** | `get_architecture`, `get_graph_schema`, `get_code_snippet`, `search_code` |
-| **Advanced** | `manage_adr`, `ingest_traces` |
+| **Indexing and coverage** | `index_repository`, `list_projects`, `delete_project`, `index_status`, `check_index_coverage` |
+| **Search and source** | `search_graph`, `search_code`, `get_code_snippet`, `get_file_outline` |
+| **Relationships and changes** | `trace_path`, `query_graph`, `detect_changes`, `compare_graphs` |
+| **Architecture and evidence** | `get_architecture`, `get_graph_schema`, `manage_adr`, `ingest_traces` |
## Performance
-Benchmarked on Apple M3 Pro:
-
-| Operation | Time |
-|-----------|------|
-| Linux kernel full index (28M LOC, 75K files) | 3 min |
-| Django full index | ~6s |
-| Cypher query | <1ms |
-| Trace call path (depth=5) | <10ms |
+Performance and context savings depend on the repository, query, machine and agent workflow. See the [scoped benchmark results](https://github.com/DeusData/codebase-memory-mcp#performance) and [methodology](https://github.com/DeusData/codebase-memory-mcp/blob/main/docs/BENCHMARK.md) for recorded measurements and limitations.
## Full Documentation
diff --git a/scripts/package-release.sh b/scripts/package-release.sh
index ff399c76d..aefaf20b3 100755
--- a/scripts/package-release.sh
+++ b/scripts/package-release.sh
@@ -293,7 +293,7 @@ build_mcpb_bundle() {
"name": "codebase-memory-mcp",
"display_name": "Codebase Memory",
"version": "$mcpb_version",
- "description": "Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.",
+ "description": "Local code intelligence connecting code, docs and infrastructure for developers and AI agents.",
"author": { "name": "DeusData", "url": "https://github.com/DeusData" },
"repository": { "type": "git", "url": "https://github.com/DeusData/codebase-memory-mcp" },
"homepage": "https://deusdata.github.io/codebase-memory-mcp/",
diff --git a/server.json b/server.json
index 91a46a646..2313e40ab 100644
--- a/server.json
+++ b/server.json
@@ -2,7 +2,7 @@
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.DeusData/codebase-memory-mcp",
"title": "Codebase Memory",
- "description": "Codebase knowledge graph for AI agents \u2014 162 languages, sub-ms queries, 99% fewer tokens.",
+ "description": "Local code intelligence connecting code, docs and infrastructure for developers and AI agents.",
"repository": {
"url": "https://github.com/DeusData/codebase-memory-mcp",
"source": "github"