Devtoolwatch BoardGet it every Monday

Graphify review

Graphify is an AI coding assistant skill that turns a codebase, with its docs, PDFs, images and videos, into a queryable knowledge graph.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

Graphify maps a project into a knowledge graph that AI coding assistants query instead of grepping files. Graphify is for developers using Claude Code, Cursor, Codex, Gemini CLI and similar assistants. Code is parsed locally with tree-sitter, without an LLM or a vector store, and every edge is tagged as extracted or inferred.

Graphify at a glance

Category
RAG, data and memory
Maintained by
Graphify Labs (organization, @Graphify-Labs on GitHub)
License
Apache 2.0
Language
Python, TypeScript, Dockerfile
Repository
github.com/Graphify-Labs/graphify
Website
www.graphify.com
PyPI package
graphifyy 0.9.93
Latest release
v0.9.93 on GitHub, Oct 20, 2026
First published
Apr 3, 2026

What Graphify does

  • Graphify parses code with tree-sitter AST locally and deterministically, with no LLM and nothing leaving your machine.
  • Graphify resolves calls, imports, inherits and mixes_in links across about 40 languages.
  • Graphify tags every edge EXTRACTED (explicit in the source) or INFERRED (resolved by graphify).
  • Graphify splits the graph into subsystems with Leiden community detection and highlights the most-connected god nodes.
  • Graphify answers plain-language queries, traces paths between two things, and explains single concepts against graph.json.
  • Graphify maps docs, PDFs, images, and video or audio into the same graph through a semantic pass.
  • Graphify turns # NOTE: and # WHY: comments and ADR/RFC citations into nodes linked to the code.

How it works

Graphify installs as a Python CLI. Then `graphify install` registers a skill in your AI assistant. Typing `/graphify .` builds the graph into graphify-out/ as graph.html, GRAPH_REPORT.md and graph.json. The semantic pass for docs and media uses your assistant's model or a configured backend such as Ollama, OpenAI, Gemini or Anthropic. An optional MCP stdio server and Neo4j or FalkorDB push are available as extras.

How to install and start using Graphify

With uv (recommended)

uv tool install graphifyy

With pipx

pipx install graphifyy

With pip

pip install graphifyy

Requirements

  • Python 3.10 or newer
  • uv (recommended) or pipx
  • A model from your assistant or a configured API key for the semantic pass over docs, PDFs, images and video
  • Codex needs multi_agent = true under [features] in ~/.codex/config.toml for parallel extraction

First steps

  1. Install the graphifyy package with uv or pipx. The CLI command is graphify.
  2. Run graphify install once. It detects your assistant and registers the skill.
  3. In your AI assistant, type /graphify . to build the graph. Codex uses $graphify instead.
  4. Open graphify-out/graph.html in a browser, or use graphify query, path and explain from the terminal.

Who Graphify is for

  • Developers who want their AI coding assistant to query a code graph instead of grepping files
  • Teams that need local code parsing with nothing leaving their machine
  • Developers who want traceable answers, with each graph edge marked as extracted or inferred
  • Projects that mix code with docs, PDFs, and media in one graph

Limitations to know

  • Graphify needs a model or a configured API key for docs, PDFs, images and video. Only code parsing is LLM-free.
  • Graphify's PDF, office, video and Leiden support require optional extras installed separately.
  • Graphify uses sequential extraction on OpenClaw and Aider, because parallel agent support there is still early.
  • Graphify's always-on, cross-repo, SDLC-wide features are part of the separate Graphify Cloud service.

Is Graphify growing? Usage data

In the week of Oct 25–31, 2026, Graphify ranked #37 on the Devtoolwatch Board and #4 in RAG, data and memory, with a momentum score of 79 out of 100. Its main package had 480.7k downloads that week, +16% against its own 4-week average.

New GitHub stars per week for Graphify12 weeks from Aug 9, 2026: 2.5k, 2.9k, 2.8k, 2.8k, 2.2k, 2.5k, 2k, 2k, 2.1k, 2.7k, 6.8k, 5.7k new stars, an average of 3.1k a week.Aug 9week of Oct 25
New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).
Show the weekly numbers
New GitHub stars per week for Graphify
Week ofNew stars
Aug 9, 20262.5k
Aug 16, 20262.9k
Aug 23, 20262.8k
Aug 30, 20262.8k
Sep 6, 20262.2k
Sep 13, 20262.5k
Sep 20, 20262k
Sep 27, 20262k
Oct 4, 20262.1k
Oct 11, 20262.7k
Oct 18, 20266.8k
Oct 25, 20265.7k

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

Graphify alternatives

Other RAG, data and memory tools on the Board in the week of Oct 25–31, 2026, by momentum:

RAG, data and memory ranked by momentum, the week of Oct 25–31, 2026
RankToolStarsDownloads/wk
#1XERJXERJ is a local-first search engine and MCP server for AI agents, packaged as one Rust binary with an Elasticsearch-compatible API.17.9k–
#2MemvidMemvid is a single-file memory layer for AI agents that packages data, embeddings, search indexes, and metadata into one portable .mv2 file.17.3k–
#3LEANNLEANN is a Python vector database and RAG library that recomputes embeddings on demand to keep indexes small on personal devices.13.7k–
#5MarkItDownMarkItDown is a lightweight Python utility from Microsoft that converts PDFs, Office documents, images, audio and other files to…193.2k4.7M
#6FirecrawlFirecrawl is an API and open source project to search, scrape, crawl, and interact with web pages, returning LLM-ready markdown or JSON…197.4k2.9M
#7Mem0Mem0 is a memory layer for AI agents and apps that stores and retrieves user, session, and agent context across interactions.68.2k884.1k

All RAG, data and memory tools, ranked

Recent Graphify releases

Graphify FAQ

Is Graphify free and open source?

Yes. Graphify's source code is on GitHub (Graphify-Labs/graphify) under the Apache 2.0 license, so you can use it for free. Its website also links to a pricing page (https://www.graphify.com/pricing) for any paid plans.

How do I install Graphify?

Run uv tool install graphifyy. The graphifyy package needs Python 3.10 or newer. The install section above has the other options from the project's README.

Is Graphify still maintained?

Yes. The Graphify-Labs/graphify repository was last updated on Oct 21, 2026, and the latest release, v0.9.93 on GitHub, came out on Oct 20, 2026.

How popular is Graphify?

Graphify has 140k GitHub stars as of Nov 1, 2026. It gained 5.7k new stars in the week of Oct 25–31, 2026, against a 12-week average of 3.1k a week. Its main package had 480.7k downloads that week, +16% against its own 4-week average. That made it #4 among RAG, data and memory tools on the Devtoolwatch Board.

Graphify vs codebase-memory-mcp: how do they compare?

Graphify and codebase-memory-mcp are both tracked by Devtoolwatch. Graphify has 140k GitHub stars and codebase-memory-mcp has 47.9k. codebase-memory-mcp review.

What are the best alternatives to Graphify?

Other RAG, data and memory tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: XERJ (#1), Memvid (#2), LEANN (#3), MarkItDown (#5), Firecrawl (#6). The alternatives table above has their numbers.

How do I use Graphify with Claude Code?

Graphify works with Claude Code after you install the graphifyy package and run graphify install, which registers the skill. Then type /graphify . in Claude Code to build the graph.

How do I use Graphify with Codex?

Graphify installs for Codex with graphify install --platform codex. In Codex you invoke it as $graphify instead of /graphify. Set multi_agent = true under [features] in ~/.codex/config.toml for parallel extraction.

How do I use Graphify with Cursor or VS Code?

Graphify installs for Cursor with graphify cursor install. For VS Code Copilot Chat, use graphify vscode install. GitHub Copilot CLI uses graphify install --platform copilot.

How do I use Graphify in Google Antigravity or OpenCode?

Graphify installs for Google Antigravity with graphify antigravity install. For OpenCode, run graphify install --platform opencode.

Is Graphify safe for private code?

Graphify parses code locally with tree-sitter, with no LLM, and nothing leaves your machine. Only the semantic pass over docs and media calls a backend, and only if you configure one.

Does Graphify work with Obsidian?

Graphify resolves Obsidian vault-relative wikilinks as of release v0.9.93. The sources do not describe a dedicated Obsidian integration.

Sources

  1. Graphify-Labs/graphify on GitHub
  2. Graphify README
  3. graphifyy on PyPI
  4. Graphify website
  5. Release v0.9.93 (Oct 20, 2026)
  6. Release v0.9.92 (Oct 16, 2026)
  7. Release v0.9.91 (Oct 14, 2026)
  8. Devtoolwatch Board, the week of Oct 25–31, 2026

Graphify README badge

Maintainers can show the tool's weekly Board rank in their README:

Devtoolwatch badge for Graphify

[![Devtoolwatch](https://index.devtoolwatch.com/badge/graphify-labs-graphify.svg)](https://index.devtoolwatch.com/tools/graphify-labs-graphify/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].