code-review

alibaba/open-code-review

Alibaba open-sources its internal code review engine — Alibaba has open-sourced the hybrid code review tool used internally at its own scale, combining deterministic rule pipelines with an LLM agent for precise, line-level comments. It ships built-in multi-language rules for issues like NPEs, thread-safety, XSS and SQL injection, and works with OpenAI or Anthropic models—useful for teams wanting battle-tested automated review without building rules from scratch.

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

tirth8205/code-review-graph

A local knowledge graph that feeds AI reviewers only relevant code — Builds a persistent, local-first graph of your codebase using tree-sitter and static analysis, exposed via MCP so AI coding tools like Claude read only relevant context instead of whole files. Aimed at developers doing code review or working in large repos, with benchmarked reductions in context size.

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

backnotprop/plannotator

A visual annotation layer for reviewing coding agent plans — Plannotator lets you markup and review agent-generated plans, markdown specs, HTML artifacts, and code diffs before implementation, then send comments straight back to the agent. It works across many CLI agents including Claude Code, Codex, Amp, Gemini CLI, and OpenCode, making it useful for teams coordinating multiple AI coding tools.

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

Gentleman-Programming/gentle-ai

A deterministic layer that gives your AI coding agent memory and proof — Gentle-AI configures 17 existing coding agents (Claude Code, Cursor, OpenCode, Codex, Pi, etc.) with persistent memory, Organic-Driven Development workflows, curated skills, MCP servers and personas. It adds evidence of what the agent did instead of asking you to trust it, and avoids locking you into one agent.

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

michael-denyer/pstack-claude

Porting Cursor's pstack skill stack to every major coding agent — This repo ports Lauren Tan's pstack, an opinionated Cursor skill stack, to Claude Code, Codex, Pi, Copilot, Gemini and others. It tracks upstream changes plus named policy forks, and adds a formal-verification skill for concurrency bugs tests can't catch. Useful for anyone running multiple agent harnesses who wants consistent, verified workflows.

Claude Code, Codex, Copilot, Pi, OpenCode, Muse, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

morganlinton/BeautifulRust

Agent Skills that teach coding agents idiomatic Rust — Three Agent Skills plus a tested clippy config teach Claude Code, Codex, Copilot, Cursor, or Gemini CLI to write, review, and port idiomatic Rust. Guidance is distilled from five major style sources (Google, Rust API Guidelines, Effective Rust, Rust Design Patterns, Microsoft), with the skill picking a side when they disagree.

Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.

kdlbs/kandev

A kanban-style control room for orchestrating coding agents — Kandev lets you organize parallel tasks across kanban/pipeline views and assign AI agents from multiple providers, with an integrated workspace (editor, terminal, browser preview, git diff) for reviewing their output. It ships as a self-hostable Go binary with no telemetry, aimed at power users who want fine-grained control over agent workflows and review gates rather than juggling separate terminal TUIs.

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

YoanWai/agent-manager

One tmux dashboard to run every AI coding agent at once — A terminal UI built with Bubble Tea that lets developers manage multiple AI coding agents (Claude Code, Codex, Gemini CLI, Grok, OpenCode) from one tmux-based dashboard, with live status, quick prompts, git worktrees, and diff review. Useful for anyone juggling several AI agents who wants a single terminal workflow instead of switching windows.

The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI. Discord: discord.gg/ecS88An7pF

pullboard-dev/pullboard

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.

razorpay/slashdocs

Turn agent output into reviewable HTML docs, not chat dumps — slashdocs is a self-hosted server, CLI, and remote MCP endpoint where AI agents publish self-contained HTML reports, specs, and diagrams. Humans comment directly on the text, agents read feedback and push new versions, and every version is kept immutable. Built for teams mixing Claude Code or other agents with human reviewers.

Give your agents the power to publish reviewable HTML documents. Self-hosted server + CLI + remote MCP; agents push, humans review with comments and versions.

init-co-jp/diff-tour

A guided, LLM-written tour through your git diffs — diff-tour turns a git change into a step-through TUI tour: it explains intent, points to where to focus (including unchanged files), and poses reviewer-style questions with answers. Built for code review, onboarding, and learning from PRs, using an LLM like Claude Code or Codex CLI to write each tour.

Walk through a diff the way a senior engineer reads it. A read-only TUI that turns a git change into a guided tour.

winnin/farol

A risk map for pull requests, sitting after your AI reviewer — farol is a free CLI and GitHub Action that runs after AI code review to show approvers which files carry the real risk of a merge, what they reach, diff coverage, and contract breaks. It relies on static analysis rather than model guesses, covering TypeScript/React, Go, and Python, and runs in shadow mode so it never blocks merges.

Know the risk of merging a pull request, and where it lives. Free, open-source CLI and GitHub Action: after your AI review, farol shows the riskiest files, what they reach, diff coverage and contract breaks. TypeScript/React, Go, Python.