# pullfrog/pullfrog

Open-source model-agnostic BYOK GitHub bot that runs in GitHub Actions

Repository: https://github.com/pullfrog/pullfrog
Canonical: https://ross.abutalabs.com/products/pullfrog
Homepage: https://pullfrog.com
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-09-02T23:14:48+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 28
- inputs: {"age_days": 393, "days_push": 0, "days_rel": 1, "gap_med": 0, "n_releases_24m": 242}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1111, forks 69 (observed 2026-09-03T02:15:17.127158+00:00)

## What it is
Pullfrog is an open-source, model-agnostic GitHub bot that runs coding agents (Claude, Codex, etc.) inside your repo's GitHub Actions. It triggers agent runs via @mentions, web dashboard prompts, or automated event triggers to implement code, review PRs, triage issues, and autofix CI failures.

## Use cases
- automate code review of new pull requests
- have an AI agent implement issues and open PRs
- auto-fix CI failures and merge conflicts
- triage and label new GitHub issues automatically
- trigger coding agent tasks by tagging @pullfrog in comments
- address PR review comments automatically
- generate release notes on commits to main

## When to choose
- you want AI-assisted coding, review, and issue triage directly inside GitHub without a separate UI
- you want to use your existing LLM provider keys or Claude/Codex subscription plans (BYOK)
- your team wants GitHub to remain the single source of truth for permissions and access control
- you want self-healing PRs that respond to CI failures and reviews automatically

## When to avoid
- you need real-time, interactive pair-programming rather than asynchronous GitHub-based agent runs
- you don't use GitHub or GitHub Actions for your workflow
- you're uncomfortable with an agent having write access to your repository
- you need fully offline or self-hosted-only agent execution without any external service

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, mcp, code-review, ci-cd, workflow-automation, llm-inference, webhook
- domain: developer-tools, version-control, large-language-models
- platform: cloud, self-hosted
- tags: github-bot, github-actions, byok, coding-agent, pr-review, issue-triage, ci-autofix, orchestration, ai-agents, automation, web-server, nodejs

## Member repositories
- pullfrog/pullfrog (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:17.127158+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:52.148541+00:00, confidence not recorded.
  - readme: https://github.com/pullfrog/pullfrog (fetched 2026-09-03T02:15:17.127158+00:00, sha e0cd4237dfd8)
  - homepage: https://pullfrog.com (fetched 2026-08-29T12:56:05.092402+00:00, sha b13e51688d49)
  - site_page: https://docs.pullfrog.com (fetched 2026-08-29T12:56:05.102209+00:00, sha 98198a6db43b)
  - registry_npm: https://registry.npmjs.org/pullfrog (fetched 2026-08-29T12:56:05.106200+00:00, sha 2897bbd70afa)
  - site_page: https://pullfrog.com/console (fetched 2026-08-29T12:56:05.104467+00:00, sha d87fecf1cec7)
- Data as of 2026-08-30T08:39:29.467469+00:00.