Generate documentation for a codebase automatically instead of writing it by hand.
Keep existing docs up to date by refreshing only the parts that changed.
Run a fast, AI free scan mode to get instant documentation from source code parsing alone.
Set up a scheduled GitHub Action that opens a pull request with refreshed docs.
| sonyarianto/wakawiki | 6elphegor/warp | adoslabsproject-gif/liara-toolkit | |
|---|---|---|---|
| Stars | 4 | 4 | 4 |
| Language | Rust | Rust | Rust |
| Setup difficulty | easy | easy | hard |
| Complexity | 2/5 | 5/5 | 4/5 |
| Audience | developer | researcher | developer |
Figures from each repo's GitHub metadata at analysis time.
Most providers need an API key, but the opencode provider works with no API key at all.
WakaWiki is a command line tool that writes and keeps up documentation for your codebase, built in Rust. Instead of you writing docs by hand, an AI agent explores your project, reads the files, searches for patterns, and produces structured documentation on its own. The project was inspired by OpenWiki. You can install it with npm or with cargo, Rust's package manager, or build it from source. Once installed, you run wakawiki --init to pick and configure an AI provider. Supported providers include OpenAI, Anthropic, DeepSeek, and OpenRouter, all of which need an API key, plus a local option called opencode that needs no API key at all. After setup, running wakawiki alone starts an interactive documentation session, while wakawiki -p lets you run it once with a specific instruction, useful for automated scripts. The tool works through a loop where it lists files, reads them, searches the codebase, and writes documentation as it goes. If you already have docs and only want to refresh what changed, the --update flag updates just those parts instead of starting over. There is also a --scan mode that skips the AI model entirely and generates instant documentation just by parsing the source code directly, which is fast and predictable but less detailed. Output lands in a wakawiki folder containing an overview file, an architecture file, and other module specific documents, along with a metadata file used to track future updates. It also creates or updates an AGENTS.md file so that AI coding agents know where to find the documentation. The project includes a ready made GitHub Actions workflow so documentation can be regenerated automatically on a schedule and submitted as a pull request. Configuration, including your chosen provider and API key, is stored in a local config file or set through environment variables. WakaWiki is released under the MIT License, so it can be used and modified freely.
A command line tool where an AI agent explores your codebase and writes structured documentation for it automatically, with an option to update only what changed.
Mainly Rust. The stack also includes Rust, npm, Cargo.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.