Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Python ai-agentsantigravityastclaude-codecode-analysiscode-searchcodexcursordeveloper-toolsgeminigraphifygraphragknowledge-graphleidenllmmcpopenclawragskillstree-sitter
fix test_watch: update import after _run_update renamed to _notify_only
Safi2a8b6c16adbc
diff --git a/README.md b/README.mdindex e89fbaa42..3a9f065a5 100644--- a/README.md+++ b/README.md@@ -96,7 +96,7 @@ Works with any mix of file types:**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files.-**Auto-sync** (`--watch`) - run in a background terminal and the graph updates itself as your codebase changes. Code file saves trigger an instant rebuild (AST only, no LLM). Doc/image changes notify you to run `--update` for the LLM re-pass. Useful for agentic workflows where multiple agents are writing code in parallel — the graph stays current between waves automatically.+**Auto-sync** (`--watch`) - run in a background terminal and the graph updates itself as your codebase changes. Code file saves trigger an instant rebuild (AST only, no LLM). Doc/image changes notify you to run `--update` for the LLM re-pass. Useful for agentic workflows where multiple agents are writing code in parallel - the graph stays current between waves automatically.**Wiki** (`--wiki`) - Wikipedia-style markdown articles per community and god node, with an `index.md` entry point. Point any agent at `index.md` and it can navigate the knowledge base by reading files instead of parsing JSON.@@ -110,7 +110,7 @@ Every edge is tagged `EXTRACTED`, `INFERRED`, or `AMBIGUOUS` - you always know w| graphify source + Transformer paper | 4 | **5.4x** | [`worked/mixed-corpus/`](worked/mixed-corpus/) || httpx (synthetic Python library) | 6 | ~1x | [`worked/httpx/`](worked/httpx/) |-Token reduction scales with corpus size. 6 files fits in a context window anyway — graph value there is structural clarity, not compression. At 52 files (code + papers + images) you get 71x+. Each `worked/` folder has the raw input files and the actual output (`GRAPH_REPORT.md`, `graph.json`) so you can run it yourself and verify the numbers.+Token reduction scales with corpus size. 6 files fits in a context window anyway, so graph value there is structural clarity, not compression. At 52 files (code + papers + images) you get 71x+. Each `worked/` folder has the raw input files and the actual output (`GRAPH_REPORT.md`, `graph.json`) so you can run it yourself and verify the numbers.## Tech stackdiff --git a/tests/test_watch.py b/tests/test_watch.pyindex 12916832e..5f17892af 100644--- a/tests/test_watch.py+++ b/tests/test_watch.py@@ -3,26 +3,26 @@ import timefrom pathlib import Pathimport pytest-from graphify.watch import _run_update, _WATCHED_EXTENSIONS+from graphify.watch import _notify_only, _WATCHED_EXTENSIONS-# --- _run_update ---+# --- _notify_only ----def test_run_update_creates_flag(tmp_path):- _run_update(tmp_path)+def test_notify_only_creates_flag(tmp_path):+ _notify_only(tmp_path)flag = tmp_path / "graphify-out" / "needs_update"assert flag.exists()assert flag.read_text() == "1"-def test_run_update_creates_flag_dir(tmp_path):+def test_notify_only_creates_flag_dir(tmp_path):# graphify-out dir does not exist yetassert not (tmp_path / "graphify-out").exists()- _run_update(tmp_path)+ _notify_only(tmp_path)assert (tmp_path / "graphify-out").is_dir()-def test_run_update_idempotent(tmp_path):- _run_update(tmp_path)- _run_update(tmp_path)+def test_notify_only_idempotent(tmp_path):+ _notify_only(tmp_path)+ _notify_only(tmp_path)flag = tmp_path / "graphify-out" / "needs_update"assert flag.read_text() == "1"