# Introduction

> Pullfrog runs coding agents inside your GitHub repositories to review pull requests, plan issues, and write code.

Pullfrog puts a coding agent to work in your GitHub repositories.

It reviews pull requests, plans and triages issues, and writes code when you mention `@pullfrog` in a comment.

## How it works

- **The Pullfrog GitHub App** listens to your repository's events, checks who triggered each one, and decides when to start a run.
- **A `pullfrog.yml` workflow** in `.github/workflows/` runs the agent on your own GitHub Actions runners, against a checkout of your repository.
- **The [console](https://pullfrog.com/console)** holds each repository's settings: the model, which events start a run, and your instructions.

A run starts from an `@pullfrog` [mention](https://pullfrog.com/docs/prompts), from a prompt in the console or the terminal, or from an [automation](https://pullfrog.com/docs/automations): a new PR, a new issue, a review on a Pullfrog PR, or a failing CI check.

## From issue to pull request

A change goes from plan to implementation to review without leaving GitHub.

### Plan

Open an issue, and Pullfrog [checks it for duplicates and posts an implementation plan](https://pullfrog.com/docs/issues). Reply with an `@pullfrog` comment to revise the plan, or edit the comment yourself.

![A Pullfrog plan comment on an issue](https://pullfrog.com/docs/images/fibonacci_plan.png)

### Implement

Click **Implement plan**. Pullfrog creates a branch, makes the change, and opens a PR linked to the issue.

![A plan comment with its Implement plan link](https://pullfrog.com/docs/images/click_implement_plan.png)

### Review

Comment on the PR with `@pullfrog` to ask for a review or another pass. Feedback on specific lines goes in a [review thread](https://pullfrog.com/docs/addressing-reviews), so the request is anchored to that code.

![A PR comment asking Pullfrog for changes](https://pullfrog.com/docs/images/request_changes.png)

## What you get

- **Any model.** Pay through [Pullfrog Router](https://pullfrog.com/docs/router) at provider cost with no markup, bring your own API key, or use a Claude, ChatGPT, Grok, Kimi Code, or OpenCode Go subscription you already have. Some models are free.
- **Agent-agnostic.** Pullfrog runs [Claude Code for Anthropic models and OpenCode for every other provider](https://pullfrog.com/docs/models#model-resolution), with an experimental Codex harness.
- **Scoped credentials.** Each run gets repository-scoped GitHub tokens that Pullfrog revokes when the run ends. Provider keys are stored encrypted in Pullfrog or in your GitHub Actions secrets.
- **Free for individuals and open source.** Personal accounts and public repositories run free. Organizations need a [plan](https://pullfrog.com/docs/billing) for private repositories, after a 30-day trial.
- **An open-source action.** The [Pullfrog GitHub Action](https://github.com/pullfrog/pullfrog) is MIT-licensed.
