Graphify-Labs/graphify
graphify
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.
GitHub metrics
- Stars
- 126K
- +2.4K this week
- Forks
- 12K
- 30-day growth
- —
- Open issues
- 678
| Day | GitHub stars |
|---|---|
| 2026-10-04 | 123556 |
| 2026-10-10 | 125131 |
| 2026-10-13 | 125977 |
What it does
Graphify turns a software project and related material into a queryable knowledge graph. It parses code locally with tree-sitter, connects structures such as calls, imports and inheritance, and writes the result to graph.json. It can also produce an interactive graph.html viewer and a GRAPH_REPORT.md report. Queries can search the graph, explain a concept or trace a path between concepts.
Code analysis does not require an LLM or API key. Graphify distinguishes relationships extracted directly from source from relationships resolved by Graphify. It does not use embeddings or a vector store for its graph. Documents, PDFs and images can join the same graph, but their semantic processing uses an AI assistant or configured model backend rather than the code-only parser. The project also supplies a skill that can be registered with supported coding assistants including Claude Code, Cursor, Codex and Gemini CLI.
Why it matters
Graphify is aimed at codebase questions that depend on relationships across files rather than text matches alone. Its graph records calls, imports, inheritance and other links, and each relationship carries provenance indicating whether it came directly from source or was inferred. Unlike vector-search approaches, Graphify stores traversable graph data and provides query, path and explain operations against it.
Main features
- Parses code locally with tree-sitter ASTs.
- Builds cross-file call, import and inheritance relationships.
- Tags graph relationships as extracted or inferred.
- Supports query, path and explain operations.
- Exports `graph.json`, `graph.html` and `GRAPH_REPORT.md`.
- Can include docs, PDFs, images, video and audio.
- Integrates with more than 20 coding-assistant platforms.
Who it's for
- Developers exploring unfamiliar or large codebases.
- Teams that want code relationships available to AI coding assistants.
- Developers who want local, LLM-free structural analysis of source code.
- Projects that need code and supporting documents represented in one graph.
Strengths
- Code-only extraction runs locally without an LLM or API key.
- Relationship provenance separates directly extracted links from inferred ones.
- Queries operate on a graph rather than an embeddings index.
- A generated HTML file provides an interactive graph viewer.
Limitations
- Docs, PDFs and images require semantic processing through an assistant or configured backend.
- Several file formats and capabilities require optional package extras.
- After a git pull or merge, the README tells users to run `graphify update .`.
- OpenClaw and Aider use sequential extraction rather than parallel agent extraction.
Getting started
Python 3.10 or newer is required. The README recommends installing the CLI in an isolated environment with uv.
uv tool install graphifyy
Requirements: Python 3.10+; semantic extraction of docs or media needs an assistant model or configured model backend, while code-only extraction can run without an API key.
Always follow the official instructions in the README on GitHub. This overview is our summary, not a copy.
Sources
- Graphify-Labs/graphifyRepositoryPrimarygithub.com
- Graphify · the code knowledge graph for AI coding assistantsOfficial sitePrimarygraphify.com
- github.com/Graphify-Labs/graphify/blob/v8/pyproject.tomlRepositoryPrimary
Alternatives to graphify
MemPalace is a Python memory layer for AI assistants: it saves your past conversations and project files word for word on your own machine, then lets you or your agent search them by meaning. The project deliberately avoids summarizing what it stores. Records are filed into a hierarchy the authors call a palace: each person or project gets a wing, subjects inside it become rooms, and the original text sits in drawers. A search can then stay inside one wing instead of scanning everything. ChromaDB is the default vector store, and the repository ships opt-in adapters for SQLite, a native Rust engine, Milvus, Qdrant and pgvector. Day to day, you point the mempalace CLI at a code folder or at Claude Code session logs, and it indexes them. An MCP server exposes the palace to agents with 45 tools, and hooks for Claude Code, Codex CLI and Cursor save sessions on a schedule and before context compression. The README reports 96.6% recall at five on the LongMemEval benchmark using plain semantic search with no language model involved, and says the scripts to reproduce that figure are in the repository.
- Stars
- 60K
- Language
- Python
- License
- MIT
- Momentum
- +0.2% 7dEstablished
PixelRAG is a retrieval system that turns web pages, PDFs and images into screenshot tiles and searches those images instead of extracted text. It is the official code for the arXiv paper "PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation", written by researchers at Berkeley SkyLab, BAIR and Berkeley NLP. The pipeline runs in stages. pixelshot renders a document into tiles with a headless Chromium browser driven over CDP. The pixelrag command then chunks and embeds the tiles with Qwen3-VL-Embedding and LoRA adapters fine-tuned on screenshot data, builds a FAISS index, and serves search through a FastAPI app on CPU or GPU. Each stage is its own pip extra, so a project installs only the parts it uses. The team also runs a hosted index of 8.28M Wikipedia pages behind a live API, which takes text or image queries; the README says it needs no API key. The renderer doubles as a Claude Code plugin called pixelbrowse, which has Claude screenshot a page and read the image, and as an npm package for opencode. Training code sits in a separate train/ project with its own pinned PyTorch and transformers versions.
- Stars
- 10K
- Language
- Python
- License
- Apache-2.0
- Momentum
- Established
turbovec is an in-process vector index for Python and Rust that stores embeddings at 2 or 4 bits per dimension and searches the compressed vectors directly. It is written in Rust with Python bindings and uses TurboQuant, a quantization method from Google Research. The README's headline figures: ten million 768-dimensional embeddings that need 31 GB as float32 fit in 4 GB, and search runs 4.4× faster than FAISS FastScan at 4-bit, at matching recall. Its benchmark table puts the 4-bit speedup at 3.8–5.1× across eight test cells on GCP ARM and x86 machines. These are the project's own benchmarks, and the scripts and raw JSON are published alongside them. No training step is needed, so a vector is searchable as soon as it is added, and removal takes microseconds. sync() writes only what changed since the last call. IdMapIndex keys vectors by your own uint64 ids and accepts an allowlist filter at query time. Drop-in stores exist for LangChain, LlamaIndex, Haystack and Agno. It is a library rather than a server, and it scans every vector instead of using a graph index.
- Stars
- 17K
- Language
- Rust
- License
- MIT
- Momentum
- Established
DigUp is a free macOS menu bar app that searches the files on your Mac by what is in them, using Google DeepMind's EmbeddingGemma 2 model running locally. You pick the folders it may read. DigUp then indexes pictures, screenshots, PDFs, documents, audio recordings and videos, and you find things by typing a plain description. A hit in a video or recording opens at the matching moment, and a PDF hit opens at the page. Exact strings such as invoice numbers and error codes are matched too, including text that Apple's Vision framework reads from screenshots. Code search is a separate index you switch on yourself: queries start with code: and results open at the line in editors such as Zed, VS Code, Cursor and Xcode. The README says nothing you index leaves the Mac. The app goes online to download the model once (865 MB) and for a daily update check that can be turned off, and it has no account and no telemetry. Internally it runs EmbeddingGemma 2 on llama.cpp with Metal and keeps vectors plus a keyword index in one SQLite file. It needs an Apple Silicon Mac on macOS 14 or later. The latest release is DigUp 0.6.0.
- Stars
- 1.5K
- Language
- Swift
- License
- MIT
- Momentum
- Emerging
Related AI tools
Clair
Coding & dev tools
Answer Claude Code permission prompts, questions and plan reviews from a Wear OS watch or an Android phone.
FreemiumFree tierVerifiedAgent Activity
Coding & dev tools
Mac app that shows what AI coding agents do in Xcode: live sessions, build timelines, errors and test results in one window.
PaidVerifiedLune
Writing & research
MCP server that grounds AI agents in full-text computer science papers from top-tier conferences, for students and researchers.
FreemiumFree tierVerified
Related guides
- Weekly digest
This week on HuiaHub: local models, MCP guides and 18 new videos
Local LLMs with Ollama and vLLM, MCP servers in Python, Claude Code hooks, 18 talks and new agent skills: everything HuiaHub published so far.
4 min read