{"slug": "give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify", "title": "Give Your AI Coding Agent a Map of Your Codebase (with Graphify)", "summary": "Graphify, an open source CLI, builds a local knowledge graph of a codebase so AI coding agents can navigate files, functions and dependencies instead of repeatedly grepping. It installs via uv, pipx or pip, supports Cursor, Claude, Codex, Gemini and Copilot, and exposes the graph to agents through a local MCP server. Each edge is tagged EXTRACTED, INFERRED or AMBIGUOUS so users can distinguish parsed relationships from guessed ones.", "body_md": "**TL;DR:** Graphify is an open source CLI that turns your codebase into a knowledge graph on your own machine. Install it with uv, pipx or pip, map your repo, and your coding agent can follow how your code actually connects instead of grepping in circles.\n\nAI coding agents are great at writing code. Where they struggle is finding their way around a real codebase. Ask about a feature on a big repo and you can watch it happen: grep, open a file, grep again, reread something it already read.\n\nThe missing piece is a map. A knowledge graph turns files, functions and concepts into nodes, and the relationships between them (calls, imports, depends on) into edges. Your agent can then jump to the right place and follow the connections.\n\nHere's how to set one up with Graphify.\n\nUse whichever installer you like. You need Python 3.10 or later.\n\n```\n# uv\nuv tool install graphifyy\n\n# pipx\npipx install graphifyy\n\n# pip, inside a virtual environment\npython3 -m venv .venv\nsource .venv/bin/activate      # Windows: .venv\\Scripts\\activate\npython -m pip install graphifyy\n```\n\nThe package is `graphifyy` (two y's) and the command is `graphify`. Check it worked:\n\n```\ngraphify --version\ngraphify install\n```\n\nThat registers the Graphify skill with the assistant it detects. To choose one explicitly:\n\n```\ngraphify install --platform cursor   # or claude, codex, gemini, copilot\n```\n\nFor Copilot in VS Code, use `graphify vscode install`. Copilot CLI uses `graphify install --platform copilot`.\n\nIn your assistant's chat, from the root of the repo:\n\n```\n/graphify .\n```\n\nIn Codex, select the skill with `$graphify` and ask it to map the current repo.\n\nYou can also skip the assistant and build a code graph from the terminal. Code only extraction doesn't need an API key:\n\n```\ngraphify extract . --code-only\n```\n\nEither way you end up with a `graphify-out/` folder:\n\n```\ngraphify-out/\n├── graph.html        Interactive graph, open it in a browser\n├── GRAPH_REPORT.md   Main concepts, communities, suggested questions\n└── graph.json        The graph the CLI and MCP tools query\n```\n\nOpen `graph.html` and click around. Then skim `GRAPH_REPORT.md`, it's a surprisingly good tour of your own project.\n\nFrom the terminal:\n\n```\ngraphify query \"how does a request reach the database?\"\n```\n\nThe result is graph context: nodes, the relations between them, and the file references to open. It is not a verified answer by itself. The default budget is 2000 tokens. Narrow a long result with `--budget 1500`, or ask about something smaller.\n\nOr just ask your agent in chat: \"using the graph, what depends on the auth module?\"\n\nOne honest note: this is context from the files Graphify analyzed. Open the lines it points to before you rely on it. Every edge is tagged `EXTRACTED`, `INFERRED` or `AMBIGUOUS`, so you can tell what was parsed from what was guessed.\n\nIf you'd rather your agent call the graph tools directly, use the local MCP server. Install the MCP extra (keep the quotes, zsh needs them):\n\n```\nuv tool install \"graphifyy[mcp]\"\n```\n\nAlready installed without it? Run `uv tool install --reinstall \"graphifyy[mcp]\"`.\n\nThen register it, always with an absolute path to the graph.\n\nClaude Code:\n\n```\nclaude mcp add --transport stdio graphify -- graphify-mcp /absolute/path/to/repo/graphify-out/graph.json\n```\n\nCodex:\n\n```\ncodex mcp add graphify -- graphify-mcp /absolute/path/to/repo/graphify-out/graph.json\n```\n\nCursor, in your user or project MCP config:\n\n```\n{\n  \"mcpServers\": {\n    \"graphify\": {\n      \"command\": \"graphify-mcp\",\n      \"args\": [\"/absolute/path/to/repo/graphify-out/graph.json\"]\n    }\n  }\n}\n```\n\nRefresh your MCP connections and ask the agent to call `graph_stats`, then `query_graph` with a question about your repo. Other clients are in the [MCP docs](https://docs.graphify.com/mcp/overview).\n\n```\ngraphify hook install\n```\n\nInstall that once in each clone. After you pull or merge, refresh the map:\n\n```\ngraphify update .\n```\n\n`graphify` not found: run `uv tool update-shell` or `pipx ensurepath`, then open a new terminal.` graphify-mcp`: use the absolute path to the executable in its config.`\"graphifyy[mcp]\"`.\nAsk your agent the same question with and without the graph, something like \"where is user input validated before it hits the database?\" Notice how many files it opens each time. That comparison tells you more than any description.\n\nFull docs are at [docs.graphify.com](https://docs.graphify.com). Graphify is open source, so if it helps you, a star on [GitHub](https://github.com/Graphify-Labs/graphify) helps other developers find it.", "url": "https://wpnews.pro/news/give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify", "canonical_source": "https://dev.to/graphify/give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify-29lg", "published_at": "2026-10-15 09:03:07+00:00", "updated_at": "2026-10-15 09:19:31.551668+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools", "agent-protocols", "mlops"], "entities": ["Graphify", "Cursor", "Claude", "Codex", "Gemini", "GitHub Copilot", "VS Code", "MCP"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify", "markdown": "https://wpnews.pro/news/give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify.md", "text": "https://wpnews.pro/news/give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify.txt", "jsonld": "https://wpnews.pro/news/give-your-ai-coding-agent-a-map-of-your-codebase-with-graphify.jsonld"}}