Patch

AI pair programming in your terminal

Website · GitHub

Patch lets you pair program with LLMs to start a new project or build on an existing codebase.

Features

Cloud and local LLMs

Patch connects to cloud and local LLMs, giving you the flexibility to use the models that work best for you.

Maps your codebase

Patch maps your entire codebase, which helps it work well in larger projects.

100+ code languages

Patch works with Python, JavaScript, TypeScript, Rust, Ruby, Go, C++, PHP, HTML, CSS, and dozens more.

Git integration

Patch automatically commits changes with sensible commit messages. Use familiar Git tools to diff, manage, and undo AI changes.

Use in your IDE

Use Patch from within your favorite IDE or editor. Ask for changes by adding comments to your code and Patch will get to work.

Images & web pages

Add images and web pages to the chat to provide visual context, screenshots, reference docs, etc.

Voice-to-code

Speak with Patch about your code. Request new features, test cases, or bug fixes using your voice and let Patch implement the changes.

Linting & testing

Automatically lint and test your code every time Patch makes changes. Patch can fix problems detected by your linters and test suites.

Copy/paste to web chat

Work with any LLM via its web chat interface. Patch streamlines copying code context and edits between your terminal and browser.

Getting Started

Install Patch from source and run the patch command:

git clone https://github.com/PierrunoYT/patch.git
cd patch
python -m pip install -e .

# Start Patch in your codebase
cd /to/your/project
patch

Security Boundaries

Patch treats both model output and the repository under edit as untrusted input.

Writes stay inside the repository. Every model-supplied path is resolved canonically and must land inside the repository root before anything is created or modified. Absolute paths, .. traversal, and symlinks pointing outside the tree are refused, including under --no-git and --yes, and including the patch format's Move to: target. Files added with --read are exempt: they are supplied by you, not the model, and are never written to.

The repository's own config is not trusted. A .patch.conf.yml or .env discovered inside the repository cannot set execution-capable options (test, test-cmd, lint-cmd, load, notifications-command, editor, verify-ssl, git-commit-verify) or environment variables that redirect API endpoints or proxies (*_API_BASE, *_BASE_URL, HTTP(S)_PROXY, REQUESTS_CA_BUNDLE, ...). Ignored settings are reported at startup. Your home-directory config and any file you pass explicitly with --config / --env-file are trusted as usual.

Pass --trust-repo-config to opt back in for a repository you trust. You can also set PATCH_TRUST_REPO_CONFIG in your shell. The setting is ignored when it comes from the repository's own config or .env, so a repository cannot grant itself trust.

Development

See CONTRIBUTING.md for local development instructions. Amp orbs use the repository's executable .agents/setup script to provision the complete development and optional-feature toolchain automatically on fresh remote machines.

More Information

Documentation

• Installation and quick start
• Security boundaries
• Development guide
• Run patch --help for all command-line and configuration options
• Report a problem or request a feature

Community & Resources

• Patch website
• Patch on GitHub
• Release notes