Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
TypeScript ai-agentsanthropicclaude-codeclicode-graphcodexcontext-engineeringcursordeveloper-toolsgeminiknowledge-graphllmmcpmcp-serveropen-sourceopenaitree-sitter
Point installer and README at the web UI
anirudhkumar-nanonetsb88b9b56ddce
diff --git a/README.md b/README.mdindex 03d62a2a..bf247565 100644--- a/README.md+++ b/README.md@@ -8,7 +8,7 @@ Dumping docs into a vector store gives you a bag of chunks. It doesn't give you- **Read** the graph before a task → get a compact, structured context bundle (entities + relationships + supporting sources), ready to drop into a prompt.- **Contribute** learnings back → new facts are deduplicated and merged into existing knowledge; repeated observations **reinforce** confidence. The graph compounds over time.-Access it three ways: as a **library**, a **CLI**, or an **MCP server** that any agent (Claude Code, Cursor, …) can plug into.+Access it four ways: a **web UI** (your team's knowledge as a living, citable graph — see below), a **library**, a **CLI**, or an **MCP server** that any agent (Claude Code, Cursor, …) can plug into.---@@ -20,7 +20,13 @@ Access it three ways: as a **library**, a **CLI**, or an **MCP server** that anycurl -fsSL https://raw.githubusercontent.com/NanoNets/context-graph-engine/main/install.sh | sh```-This puts `context-graph` and `context-graph-mcp` on your PATH. Requires git and Node ≥ 20.+This puts `context-graph`, `context-graph-mcp`, and `context-graph-web` on your PATH. Requires git and Node ≥ 20.++Or straight from GitHub with npm:++```bash+npm install -g github:NanoNets/context-graph-engine+```Or as a library / dev dependency:@@ -28,6 +34,17 @@ Or as a library / dev dependency:npm install context-graph-engine```+## Try it in 60 seconds — the web UI++```bash+context-graph-web+# → http://localhost:4680+```++Open the page, point **“Ingest a folder of documents”** at any folder of `.pdf` / `.md` / `.txt` files, and watch it become a knowledge graph. Then ask questions: answers come back with numbered citations, and every fact wears a **provenance receipt** — how many times it's been observed, how confident the graph is, and which sources say so. Use **“Teach it something”** to add a fact the docs don't capture, and watch the graph reinforce in real time.++Everything runs on your machine (the server binds to localhost only). Set `OPENROUTER_API_KEY` to upgrade to LLM-written answers and cloud extraction; without it, retrieval and the graph stay fully local.+### Runs locally by default — keys are optionalOut of the box the engine needs **no accounts and no cloud calls**:diff --git a/install.sh b/install.shindex f2df3430..8509e16e 100755--- a/install.sh+++ b/install.sh@@ -5,8 +5,9 @@# 1. From a checkout: ./install.sh (builds THIS directory — no re-clone)# 2. Over the network: curl -fsSL https://raw.githubusercontent.com/NanoNets/context-graph-engine/main/install.sh | sh#-# Either way it builds the project and puts the `context-graph` and-# `context-graph-mcp` commands on your PATH. Requires git, Node >= 20, and npm.+# Either way it builds the project and puts the `context-graph`,+# `context-graph-mcp`, and `context-graph-web` commands on your PATH.+# Requires git, Node >= 20, and npm.## Environment overrides:# CGE_REPO git URL to clone from (default: the NanoNets repo below)@@ -66,13 +67,17 @@ info "Installing dependencies"info "Building"( cd "$INSTALL_DIR" && npm run build --silent )-info "Linking the 'context-graph' and 'context-graph-mcp' commands"+info "Linking the 'context-graph', 'context-graph-mcp', and 'context-graph-web' commands"( cd "$INSTALL_DIR" && npm link >/dev/null 2>&1 )echo-info "Installed. Try: context-graph --help"+info "Installed. Try: context-graph-web"cat <<'NEXT'+ The web UI is the fastest way in:+ context-graph-web+ # → open http://localhost:4680, ingest a folder of docs, ask questions+Runs locally out of the box:• Embeddings run in-process (no key, no server — model downloads on first use).• Extraction defaults to a local Ollama model. Install Ollama and pull one: