Shippie is an MIT-licensed AI code-review agent, rebranded from Code Review GPT, built on the `flue` agent framework. The released review workflow reads pull-request or staged diffs, explores the codebase with developer tools, and posts focused findings for issues such as exposed secrets, inefficient code, potential bugs, and unhandled edge cases. It runs as a GitHub Action on pull requests, can be triggered by a trusted collaborator's `/shippie` comment, and runs locally on Node.js 22.19+ through the `shippie review` CLI or `npm run review`; a self-built HTTP server workflow is also documented. Extensibility comes from remote HTTP/SSE MCP servers, root `AGENTS.md`/`AGENT.md`/`CLAUDE.md` instruction files, Agent Skills, and flue's `task` delegation tool. Built-in model providers are Anthropic, OpenAI, OpenRouter, Cloudflare Workers AI, and Cloudflare AI Gateway; custom OpenAI-compatible providers require code registration. Lifecycle caveat: the main branch documents an autonomous `shippie qa` system for web and CLI testing, but the latest published release at verification time does not include the QA action/docs and no `v0` major tag is published, so QA should be treated as unreleased rather than generally available. Users supply their own model credentials, so code/diffs flow to the configured LLM provider and provider API charges apply. Shippie also sends default-on anonymous usage telemetry to `telemetry.shippie.dev`; documented events contain a hashed repository identifier, platform, model, OS/architecture/Node/Shippie version data and run-specific counters, but no code or file contents. Set `SHIPPIE_TELEMETRY=false` to opt out.
Shippie
Extensible open-source AI code review agent with emerging QA automation
Open-source (MIT) AI code-review agent formerly known as Code Review GPT. Its released workflow reviews pull requests in GitHub Actions or staged changes locally, supports remote MCP tools and project instruction files, and works with Anthropic, OpenAI, OpenRouter, and Cloudflare providers. The main branch also contains an unreleased autonomous QA workflow. Anonymous usage telemetry is enabled by default and can be disabled.
Pricing
Free and open-source (MIT). No Shippie subscription or hosted-service fee; users pay their chosen LLM provider's API charges and any CI or compute costs in their own environment.
Platforms
Released review workflow: GitHub Action on pull requests, trusted-collaborator `/shippie` comment trigger, local Node.js 22.19+ CLI (`shippie review` / `npm run review`), and self-built HTTP server. Remote HTTP/SSE MCP client; `AGENTS.md`/`AGENT.md`/`CLAUDE.md`, Agent Skills, and task delegation. Providers: Anthropic, OpenAI, OpenRouter, Cloudflare Workers AI, Cloudflare AI Gateway; custom OpenAI-compatible providers by code registration. Main-branch autonomous QA workflow is unreleased.
Categories
Tags
Alternatives
CodeRabbit
AI-powered code review
AI-powered code review tool that automatically analyzes pull requests and provides line-by-line feedback on code quality, bugs, security vulnerabilities, and best practices. Integrates with GitHub and GitLab as a bot that comments on PRs. Uses LLMs to understand code context and suggest improvements. Learns from your codebase patterns and team preferences. Supports all major programming languages. Reduces review cycle time while catching issues human reviewers might miss.
Greptile
AI code review with full codebase context
Greptile is a Y Combinator-backed AI code review tool that indexes your entire codebase to build a semantic code graph of functions, classes, and dependencies. Unlike diff-only reviewers, it catches cross-file issues, architectural drift, and convention violations with an 82% bug catch rate. Supports GitHub, GitLab, Jira, Slack, and VS Code. Offers cloud and self-hosted VPC deployment with SOC2 Type II compliance. Used by 250+ companies including Stripe and Amazon.
Codacy
Automated code quality
Codacy is a managed code quality, security and AI-guardrails platform for GitHub, GitLab and Bitbucket teams. It scans pull requests and repositories for quality, coverage and security issues while adding AI Inventory, AI Guardrails, AI Risk Hub, AI Reviewer and Verity beta surfaces for AI-assisted engineering.
SonarQube
Code quality and security analysis platform
SonarQube is an open-source code quality and security platform with 10K+ GitHub stars that inspects code for bugs, vulnerabilities, code smells, and security hotspots. It enforces quality gates in CI/CD pipelines, supports 30+ languages in Team plans and 40+ in Enterprise, and remains the industry standard for static code quality management.
Related Tools
Brooks-Lint
AI code review grounded in twelve classic software-engineering books
Open-source (MIT) AI reviewer with a distinctive angle: findings are grounded in twelve classic engineering books, cited by source, and framed as decay-risk diagnostics with a 0–100 Health Score. Runs as an Agent Skill across Claude Code, Gemini CLI, Codex, and other coding agents, with GitHub Actions quality gates and SARIF output.
roborev
Continuous local code-review loops for commits produced by AI coding agents
roborev is an MIT-licensed local review system that checks every commit in the background, stores findings in a review queue, and feeds actionable issues back into AI coding sessions. Git hooks, a TUI, branch and dirty-tree analysis, Codex and Claude agent hooks, plus iterative fix/refine commands turn review into a continuous agent workflow.
Mergify
Merge queue, CI insights, flaky-test controls, and stacked pull requests for GitHub teams
Mergify is a pull request automation platform that keeps main branches green with merge queue batching, merge protections, CI Insights, flaky-test detection, and stacked pull requests. Its Stacks workflow turns commits on one local branch into focused PR chains, helping teams review large AI-generated or feature-heavy changes without losing queue safety.
Baz
Telemetry-aware AI code reviewer that checks how pull requests may affect real services.
Baz is an AI code-review platform focused on production-aware pull requests. Instead of only reading the diff, Baz connects code changes to application telemetry so reviewers can understand what endpoints, services, and runtime behavior may be affected. That makes it a useful complement to existing AI PR bots when the question is not just whether a change looks correct, but whether it could break a live system.
reviewdog
Automated code review for any linter on CI
reviewdog is an open-source automated code review tool that integrates any linter or static analysis tool with GitHub, GitLab, Bitbucket, and Gitea pull requests. Parses output in errorformat, Checkstyle XML, SARIF, and JSON formats to post inline review comments on changed lines only. Works with GitHub Actions, Travis CI, CircleCI, GitLab CI, and Jenkins. Supports 40+ languages through universal linter adapter architecture.
mrge
LSP-based AI code review agent backed by Y Combinator
mrge is a YC-backed AI code review agent that uses Language Server Protocol analysis to provide deep, context-aware pull request reviews. It goes beyond surface-level pattern matching by understanding project structure, type information, and cross-file dependencies. Integrates with GitHub and GitLab to deliver automated reviews that catch logic errors, security issues, and architectural inconsistencies.