🤖 readme-ai
Generate beautiful, production-ready README files from your code using AI.
Point it at any codebase. Get a README worth starring.
✨ Features
- Understands your code — scans source files, package manifests, and directory structure; builds context before writing a single word
- Production-quality output — badges, installation instructions, real usage examples, configuration docs, contributing guide
- Smart prioritisation — reads
pyproject.toml,package.json,main.pyand similar files first so the AI leads with the most important context - 15+ languages supported — Python, TypeScript, Go, Rust, Java, C/C++, Ruby, PHP, and more
- Dry-run mode —
readme-ai scanshows exactly what the AI will see, with no API call - Multilingual output — generate in English or Russian (
--language ru) - Non-destructive — always asks before overwriting an existing README
📦 Installation
pip install readme-ai
Or with pipx for an isolated global install:
pipx install readme-ai
Requirements: Python 3.9+ · An Anthropic API key
🚀 Usage
Generate a README
# Set your API key once
export ANTHROPIC_API_KEY="sk-ant-..."
# Generate README for the current directory
readme-ai generate .
# Or point at any project
readme-ai generate ~/projects/my-app
# Preview in terminal without writing to disk
readme-ai generate . --preview
# Generate in Russian
readme-ai generate . --language ru
# Write to a custom path
readme-ai generate . --output docs/README.md
Inspect what the AI sees (no API call)
readme-ai scan .
Output:
Project: my-app
Files found: 12
Languages detected:
Python ████████████ 6
TypeScript ██████ 3
Shell ██ 1
Priority files:
★ pyproject.toml
★ main.py
★ requirements.txt
Full options
readme-ai generate [OPTIONS] [PATH]
Arguments:
PATH Project directory [default: .]
Options:
-o, --output PATH Output file path [default: <path>/README.md]
-k, --api-key TEXT Anthropic API key (or set ANTHROPIC_API_KEY)
-l, --language [en|ru] Output language [default: en]
-p, --preview Print to stdout instead of writing to file
-f, --overwrite Skip the overwrite confirmation prompt
-m, --model TEXT Claude model to use
-V, --version Show version and exit
⚙️ Configuration
| Variable | Description | Required |
|---|---|---|
ANTHROPIC_API_KEY |
Your Anthropic API key | Yes |
Get your key at console.anthropic.com.
The default model is claude-sonnet-4-20250514. You can override it with --model:
readme-ai generate . --model claude-opus-4-20250514
🔍 How it works
Your project
│
▼
📂 Scanner Reads up to 30 files, prioritising entry points
│ and package manifests. Builds a directory tree.
▼
🧠 Prompt builder Assembles structured context: tree, languages,
│ package metadata, key source files.
▼
✨ Claude AI Generates a README following strict documentation
│ best practices with real examples and badges.
▼
📄 README.md
🤝 Contributing
Contributions are welcome! Here's how to get started:
git clone https://github.com/aaxnet/readme-ai
cd readme-ai
pip install -e ".[dev]"
pytest tests/ -v
Please open an issue before starting work on a large feature. PRs should include tests.
📄 License
MIT © 2026 readme-ai contributors
Metadata
Release files for aaxnet-readme-ai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| aaxnet_readme_ai-0.1.0.tar.gz | 14.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aaxnet_readme_ai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 26.6 kB
Release files / aaxnet_readme_ai-0.1.0.tar.gz
| Download URL | aaxnet_readme_ai-0.1.0.tar.gz |
|---|---|
| Size | 14.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5d363b9446aa63ca60cb7042de3a721109949e6ce2f2b07a7fae8c92bf4e0891
|
|
BLAKE2b-256 checksum How to use checksums |
1330096b5c37de6d9f65a90921aa2e0745f857e076bd7321cef6497cf2e0a50f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Release files / aaxnet_readme_ai-0.1.0-py3-none-any.whl
| Download URL | aaxnet_readme_ai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 12.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
52d3bfd1c87e533eac504987369ce8c502dbea5769d90e1307002474fd5da036
|
|
BLAKE2b-256 checksum How to use checksums |
1e5fcb5126b0ef2486af1859e8b20e01841c61b72ab6f15085d10c995372a27c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Security for aaxnet-readme-ai 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.