ReadmeAI CLI
ReadmeAI analyzes repository files and drafts a README with a project overview, directory structure and setup guidance.
- 3,005 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The CLI reads repository files, writes docs and sends material to the selected cloud model when enabled.
Install
Manual install
pip install -U readmeaiFirst recommended Installation option.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The CLI reads repository files, writes docs and sends material to the selected cloud model when enabled.
This is third-party code. Review the repository files before installing.
What it does
ReadmeAI drafts a README from a repository URL or local directory. It analyzes files and dependencies, then builds an overview and getting-started sections with configurable styling and output. Text can use cloud models, Ollama or an offline mode without an LLM API. File exclusions are configurable. Review generated setup instructions and feature claims against the actual application.
Who it is for. Repository maintainers drafting initial project documentation from existing files.
Good fit when
- A codebase lacks a coherent README for newcomers.
- Structure and dependencies need gathering before editorial review.
- Several repositories need a consistent documentation template.
- Analysis scope needs narrowing through exclusion rules.
Not a fit when
- Instructions would be published without testing actual commands.
- Private code cannot reach the selected cloud provider.
- You need a manually controlled specification that generation must not change.
Example request
Draft this local project’s README into a new file. Exclude secrets and flag commands requiring manual verification.Limitations
Python 3.10 or newer is required, with installation extras for Anthropic and Gemini clients. Cloud models use your API key and receive analysis material, so exclude secrets and restricted files. Ollama requires a separately running local model, while offline mode uses no LLM API. Setup information inferred from repository files may not match the real environment; verify the generated instructions manually.
How to disable. Stop generation and uninstall if no longer needed. Retain the reviewed README and revoke unused provider keys.
FAQ
Can I use a local directory?
Yes. `--repository` accepts a path or repository URL; verify it first.
How do I avoid an LLM API?
Select `--api offline` and use local files for fully offline work.
How do I save elsewhere?
Set `--output` to a new filename and compare before replacing the README.
What does Ollama require?
A running Ollama server with the selected model; verify its address first.
How do I exclude files?
Use `.readmeaiignore` and verify sensitive files are excluded before cloud generation.
Discussion
No questions or reviews yet.
Related
CLI toolsThe CLI builds wikis from local or GitHub codebases, links modules and traces answers to source-file line ranges.
Multi-agent documentation generator: analyzes a repository and builds a README and AI assistant config files
A self-hosted RAG platform: cited answers over GitHub, Notion, Drive and files, with an MCP mode for Claude Code.
Docling is a CLI for mixed document archives, bringing PDFs, office files and spreadsheets into a shared format for AI search.
A skill and local renderer: an agent draws three SVG diagrams of a project from its README and sources, no keys or network needed
The plugin compiles notes or codebases into a topic wiki with source backlinks and a user-approved article structure.
README in short
GitHub, GitLab, Bitbucket and local projects are supported. Templates, badges and section styles are configurable.