Automate technical documentation generation and maintenance for any codebase using AST parsing and dependency graphs.
AutoDocs is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view TrySita/AutoDocs --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
AutoDocs automatically creates and updates technical documentation for your code. It reads your code, understands how different parts connect, and writes clear docs. It also includes a search tool that helps AI assistants understand your codebase better.
AutoDocs is an open-source tool by Sita that automates the generation and maintenance of technical documentation for any codebase. It uses tree-sitter for AST parsing and SCIP for symbol resolution to build a detailed dependency graph of your code. The tool then traverses this graph to produce accurate, dependency-aware documentation and summaries. It includes a FastAPI backend for ingestion and search, a Next.js web UI for chat and exploration, and an MCP server that allows AI coding agents to perform deep searches of your codebase via HTTP. AutoDocs supports multiple languages and is designed to keep documentation in sync with code changes, reducing the manual effort of documenting complex projects.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 1 days ago.
198 GitHub stars indicate community interest.
2 open issues signal maintenance load.
Apache-2.0 license detected.
Automatically generate API documentation for a Python web framework.
Maintain up-to-date internal documentation for a large monorepo.
Provide context-aware search for AI coding assistants like Claude or Copilot.
Create dependency graphs and summaries for onboarding new developers.
Generate documentation for legacy codebases with minimal manual input.
Requires a GitHub Personal Access Token for private repositories; ensure token is kept secure.
Running locally may expose sensitive code if not properly sandboxed.
198
Stars
14
Forks
2
Issues
Apache-2.0
License
Optimize markdown documentation for LLMs and RAG systems, reducing token consumption by 67-95%.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
Turn OpenAPI, MCP, Doxygen, godoc, rustdoc, and Markdown into static documentation sites you own.
2 security/trust notes recorded.
Setup difficulty is 3/5.