agent-wiki-cli

LLM Wiki CLI

Build and maintain an architectural wiki for your codebase. LLM Wiki scans source into Markdown pages, keeps generated structure in sync, and supplies coding agents with searchable, bounded context. Agents add the explanations and guides that static analysis cannot provide.

The PyPI package is agent-wiki-cli, the command is llm-wiki, and the Python import package is llm_wiki_cli.

Quick start · Examples · Command reference · Standalone documentation

Installation

Requires Python 3.10 or later.

pip install agent-wiki-cli

For MCP support, install pip install "agent-wiki-cli[mcp]". Installation options cover source checkouts and optional dependencies. To remove the package, run pip uninstall agent-wiki-cli.

Quick Start

Run these commands from your project root. Choose generic for an AGENTS.md instruction file, or select one of the supported agents.

llm-wiki init --agent generic --prepare-extractors

--prepare-extractors automatically prepares missing or stale helpers for the selected TypeScript/JavaScript, Go, Rust, or Haskell source files and reuses current helpers. Install the relevant toolchain first: Node.js with npm, Go, Cargo, or GHC. Python needs no helper. Helper setup may download dependencies or compile a bundled helper. Omit the flag to scaffold without preparation; read-only commands never prepare helpers. You can rerun the setup command after a package upgrade or use llm-wiki prepare-extractors --src-dir . separately.

llm-wiki bootstrap --src-dir . --wiki-dir docs/llm_wiki

Bootstrap selects current compressed native storage and indexed maintenance ownership automatically. Task and compact-view requests can omit version fields; the library selects current contracts. Existing projects receive these defaults by updating the package and running llm-wiki upgrade from their project root. Upgrade retains recovery copies and reports their locations.

Open docs/llm_wiki/index.md to browse the wiki. Use your coding agent to enrich semantic descriptions, guides, and behavior notes; generated diagrams, tables, and machine-readable artifacts are maintained by the CLI.

After source changes, update and validate the wiki:

llm-wiki sync --src-dir . --wiki-dir docs/llm_wiki --jobs 1
llm-wiki lint --strict --src-dir . --wiki-dir docs/llm_wiki --jobs 1

For an isolated documentation workspace from source or an existing enriched wiki, follow the standalone documentation guide.

For a small project you can copy and change, try the Python, FastAPI, Go, and plugin tutorials. They show the generated pages, a source edit, and the next sync without requiring a model service.

What It Creates

The default docs/llm_wiki/ contains an index, module and entity pages, workflows, user flows, guides, and a change log. Depending on the source and options, it also includes infrastructure, API contracts, dependency, and load-order pages. Generated structure and agent-authored prose share one canonical wiki.

See the wiki guide for the page taxonomy, content ownership, generated artifacts, and Python API. Export the same wiki for Obsidian or a static site.

Supported Inputs

Discovery honors .gitignore. Use a source-selection profile to restrict the source boundary. See input details for helper requirements and language-specific behavior.

Agent Support

Choose claude, aider, opencode, copilot, cursor, or generic during initialization. Every agent can use explicit sync, lint, and reviewed prompts; LLM Wiki does not install Git hooks.

Agent setup explains instruction files and skill export. Workflow installation and upgrades cover setup in another project, all agent targets, and the --no-skills inline fallback. The MCP server provides read-only wiki access, and bundled skills guide documentation and analysis workflows.

Common Workflows

Automation

Install a read-only GitHub Actions integrity gate after creating your wiki. The automation guide covers the immutable release reference, permissions, helper preparation, and advisory PR impact reports. It also covers optional health dashboards and manual agent triggers.

Command Reference

The command reference contains complete workflows, output formats, exit codes, migration guidance, and resource controls. Use llm-wiki <command> --help for available options.

Security Model

Built-in extraction reads source without importing the target application. Project plugins are trusted Python code, and manual agent triggers use the agent's own permissions. Review generated prompts before sharing sensitive source. See the security model and vulnerability reporting policy.

Contribution Policy

This project does not maintain a formal contribution process. You are welcome to freely fork it, adapt it to your workflow, and publish your own changes under the MIT license. Community interactions follow the code of conduct.