Pullfrog, an open-source AI-powered GitHub bot created by Colin McDonnell, is in beta, positioning itself as a model-agnostic alternative to CodeRabbit that runs entirely within GitHub Actions.
McDonnell, best known as the creator of Zod, the TypeScript-first schema validation library with over 42,000 GitHub stars, announced Pullfrog on May 12, 2026. The tool is designed as an orchestration layer for asynchronous development inside GitHub, listening for webhooks and triggering AI agent runs based on configurable events such as new pull requests, issues, CI failures, and review submissions.
Unlike CodeRabbit, which operates as a hosted SaaS platform with its own AI models, Pullfrog takes a bring-your-own-key (BYOK) approach. Developers can connect any LLM provider including Anthropic, OpenAI, Google, Mistral, DeepSeek, and OpenRouter, switching between models with a single configuration change. All API keys are stored using GitHub's secret management system, and agent runs execute in the repository's own GitHub Actions environment via a dedicated pullfrog.yml workflow file.
Getting started requires installing the Pullfrog GitHub App and adding the workflow file to a repository.
Developers can then tag @pullfrog in any issue, pull request, or comment to trigger an agent run, or configure automated triggers from the Pullfrog console. The full setup guide is available in the official documentation.
The agent ships with a purpose-built MCP server for performing git and GitHub operations such as creating pull requests, leaving reviews, reading CI logs, and managing issues. Shell commands run in an isolated subprocess without access to sensitive environment variables. A headless browser tool is also included out of the box, enabling the agent to run end-to-end tests, take screenshots, and iterate on UI without additional configuration.
The competitive landscape for AI code review has grown significantly in recent months. CodeRabbit has been the established leader in purpose-built code review since 2023, while GitHub Copilot's code review capabilities launched in April 2025 and saw rapid adoption driven by native platform integration. Other tools such as Greptile and Bito also compete in the space. Where Pullfrog differentiates itself is in its open-source licensing, model agnosticism, and broader scope that extends beyond code review into issue triage, CI autofix, merge conflict resolution, and plan generation.
Community response to the announcement attracted over 50 replies and over 1,000 likes. One user asked:
Can it be ran locally for agentic workflows before it’s pushed to github or in cloud agents?
To which the McDonnell replied:
Pullfrog is a harness over OpenCode & Claude Code intended to be run in CI
for local development you can just use these directly and give them access to git and the gh CLI. we'll add a CLI shortly that'll let you quickly spin up "cloud agents" that are running in GH Actions but we're not trying to be an agent that you use for local dev
Pullfrog is an open-source AI-powered GitHub bot created by Colin McDonnell, best known as the author of Zod. It provides model-agnostic, agent-based automation for pull request review, issue triage, and CI remediation, running entirely within GitHub Actions rather than requiring a hosted third-party service. The project's source code has accumulated over 400 stars since its initial preview in late 2025.