Turn any folder of code, docs, papers, images, or videos into a queryable graph with a local knowledge graph engine for AI coding assistants. Type /tracely360 in your AI coding assistant and it builds a map of structure, dependencies, and design context you can actually navigate.
pip install tracely360$ pip install tracely360 && tracely360 install$ /tracely360 ./my-project Scanning corpus... 127 files (Python, TypeScript, Go) ✓ 1,842 nodes · 3,291 edges ✓ 12 communities detected ✓ God nodes: AuthService, UserRepo, APIGateway ✓ Surprise: RateLimiter → CacheLayer ✓ 14 API endpoints mapped (FastAPI, Express) Outputs → tracely360-out/ graph.html graph.json GRAPH_REPORT.md Query cost: 2.1k tokens (vs 148k raw) · 70× reduction
tracely360 is an open-source local knowledge-graph engine that transforms folders of code, documentation, images, and media into queryable, interactive knowledge graphs for AI coding assistants.
The core extraction runs entirely offline using tree-sitter and static analysis, so teams can understand large codebases without shipping raw source code to a hosted indexing service. An optional second pass can add semantic meaning from documentation to the same graph.
Install it with pip install tracely360, run tracely360 install, then use /tracely360 . as a slash command inside Claude Code, Codex, Cursor, and Copilot-style assistants.
That gives you a multi-modal code and docs graph that reduces tokens for AI coding assistants while preserving relationships, provenance, and architectural intent.
tracely360 unifies static analysis, semantic extraction, and graph clustering into a single skill any AI coding assistant can invoke.
25 languages via tree-sitter: Python, JS, TS, Go, Rust, Java, C/C++, Ruby, C#, Kotlin, Scala, PHP, Swift, Lua, Zig, and more. Two-pass extraction for cross-file resolution.
Merges extracted nodes and edges into a NetworkX graph. Leiden community detection groups related concepts by topology — no LLM calls, no embeddings required.
Identifies the highest-degree god nodes at the heart of your system. Flags unexpected cross-community edges worth investigating, each with a plain-English explanation.
Static analysis of route decorators across 13 frameworks: Flask, FastAPI, Django, Express, NestJS, Next.js, Spring, Laravel, Rails, Gin, Echo, Chi, ASP.NET. No code execution.
Code, markdown, PDFs, images, screenshots, diagrams, whiteboard photos, video, and audio. Video/audio transcribed via faster-whisper with domain-aware prompts.
graph.html (vis.js visualization), GRAPH_REPORT.md (one-page audit), graph.json (persistent queryable graph), and wiki/ (Obsidian-compatible vault with bidirectional wikilinks).
tracely360 ships as a slash command. Type /tracely360 . in any supported assistant. It writes tracely360-out/ and queries read the graph instead of raw files.
MCP Server tools
query_graphNatural language queryget_nodeFull node detailsget_neighborsAdjacency lookupget_communityCommunity membersgod_nodesTop connected nodesgraph_statsGraph summaryshortest_pathPath between nodesEach stage is an isolated module. Contributors can extend any step independently without touching the rest of the pipeline.
tracely360 is distributed on PyPI. Install it, run tracely360 install to auto-detect your AI assistant, then type /tracely360 . to build your first graph.
Output structure
tracely360-out/ ├── GRAPH_REPORT.md ← one-page audit ├── graph.json ← persistent graph ├── graph.html ← interactive viz ├── wiki/ ← Obsidian vault └── cache/ ← incremental cache
Optional extras
# Requires Python 3.10+pip install tracely360tracely360 install # auto-detects your AI assistant# In your AI coding assistant:/tracely360 . # build graph for current folder/tracely360 --update # incremental rebuild/tracely360 --wiki # generate Obsidian vault# CLI utilities:tracely360 query "How is AuthController connected?"tracely360 path "AuthService" "UserRepository"tracely360 watch # auto-rebuild on file changes
The repository ships with reproducible corpora demonstrating tracely360 on both small libraries and large mixed code-and-paper collections.
God nodes
Surprise edge: DigestAuth → Response (cross-community)
Avg query: ~1.7k tokens vs ~123k reading raw files. 3 GPT repos + 5 attention papers + 4 diagrams.
| Tool | Purpose | Strength | Limitation vs tracely360 |
|---|---|---|---|
| tracely360 | Local knowledge graph for AI assistants | Multi-modal, offline, 14 platform integrations | — |
| Sourcegraph | Cross-repo code search | Enterprise-grade navigation | Not a knowledge graph; no design semantics |
| Code2Vec | Function-level embeddings | Vector retrieval & classification | No graph structure, no multi-modal input |
| Neo4j | General graph database | Powerful Cypher queries | Does not generate graphs from code itself |
tracely360 is released under the Apache 2.0 License. Its core dependencies — NetworkX (BSD-3) and tree-sitter (MIT) — are all permissive open-source licenses with no conflicts. The project performs no telemetry.
The only outbound network call is the optional semantic-extraction step, which uses your own configured AI model API key. Only semantic descriptions of documents are transmitted — never raw source code.
Only semantic summaries sent to LLMs. AST extraction is 100% local.
URL fetching restricted to http/https, size- and time-bounded via security.py.
All output paths are containment-checked before write.
Node labels are HTML-escaped before being written into graph.html.
Zero analytics, zero beacons, zero external pings beyond your own LLM key.
Commercial use, modification, and distribution permitted with no restrictions.
Why structural graphs beat vector RAG for code understanding.
Read the full guide on knowledge graphs for AI coding assistants →Every /tracely360 and tracely360 command in one place.
Read the full CLI reference for tracely360 →Claude Code, Codex, Cursor, MCP server, and git hooks step by step.
Read the AI coding assistant integration guide →Honest comparison against Sourcegraph, Code2Vec, and Neo4j.
Read the tracely360 comparison guide →No. The AST extraction pass runs entirely locally using tree-sitter — no network calls, no API keys required. Only during the optional semantic extraction step are semantic summaries of documents sent to an LLM, never raw source code.
14 platforms: Claude Code, OpenAI Codex, OpenCode, Aider, Cursor, VS Code Copilot Chat, GitHub Copilot CLI, OpenClaw, Factory Droid, Trae, Gemini CLI, Hermes, Kiro, and Google Antigravity. Each has a matching install command.
Leiden clustering uses approximate betweenness centrality sampling for graphs over 5,000 nodes. Per-file SHA256 caching means incremental rebuilds only process changed files, so subsequent updates are fast regardless of total codebase size.
Yes. tracely360 is released under the Apache 2.0 License, which permits commercial use, modification, and distribution. Its core dependencies — NetworkX (BSD-3) and tree-sitter (MIT) — are equally permissive.
Not manually. Run tracely360 hook install once to set up post-commit and post-checkout git hooks that auto-rebuild the AST graph. Alternatively, tracely360 watch gives real-time file-system monitoring.