← Use cases · Coding agents & IDE assistants
AI agent tools for code review
Short answer: Our top pick for code review: code-review-graph, with the highest AgentPick Score (82/100) among tools tagged "code-review". Runners-up: plannotator (82) and gentle-ai (81). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | code-review-graph | 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 benchmar… | 82/100 | ★ 32k | MIT | 6 Oct 2026 |
| #2 | plannotator | Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click. | 82/100 | ★ 9.4k | Apache-2.0 | 15 Oct 2026 |
| #3 | gentle-ai | Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Drive… | 81/100 | ★ 7.8k | MIT | 14 Oct 2026 |
| #4 | zeroshot | Enforced QA for Claude Code, Codex and Copilot. Draw the graph: code review, your own reviewers and test agents, any model per node. Slop goes back to… | 73/100 | ★ 2k | MIT | 14 Oct 2026 |
| #5 | gentle-shell | Your coding agent for controlled development in the workspace you lead. A Pi-native shell with Organic Driven Development, focused subagents, risk-bas… | 72/100 | ★ 1.3k | MIT | 14 Oct 2026 |
| #6 | pstack-claude | Claude Code, Codex, Copilot, Pi, OpenCode, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives transl… | 70/100 | ★ 2k | MIT | 14 Oct 2026 |
| #7 | crit | Review AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent. | 69/100 | ★ 1.2k | MIT | 12 Oct 2026 |
| #8 | agent-manager | The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI. | 68/100 | ★ 594 | Apache-2.0 | 14 Oct 2026 |
| #9 | pilot-shell | Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, pers… | 67/100 | ★ 2.1k | See repo | 14 Oct 2026 |
| #10 | dscode | A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry | 67/100 | ★ 995 | MIT | 14 Oct 2026 |
| #11 | kandev | AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry. | 67/100 | ★ 952 | AGPL-3.0 | 15 Oct 2026 |
| #12 | sno-station | Turn the agents you already use into a squad. Codex, Claude Code, Cursor, Hermes Agent and OpenClaw use one encrypted memory, pass work to each other,… | 67/100 | ★ 730 | Apache-2.0 | 14 Oct 2026 |
| #13 | flow-next | Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by … | 67/100 | ★ 709 | MIT | 14 Oct 2026 |
| #14 | agentsys | AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro. | 66/100 | ★ 998 | MIT | 14 Oct 2026 |
| #15 | openqodex | Open source code review that runs in your coding agent before you push. Scanners plus a separate AI reviewer, on your own login, no key. | 66/100 | ★ 699 | Apache-2.0 | 15 Oct 2026 |
| #16 | kodus-ai | Open source, self-hosted AI code review. Bring your own LLM. | 65/100 | ★ 1.5k | See repo | 14 Oct 2026 |
| #17 | git-lrc | Free, Micro AI Code Reviews That Run on Git Commit | 65/100 | ★ 1.5k | See repo | 11 Oct 2026 |
| #18 | autoprompt-skill | Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks. | 64/100 | ★ 1.2k | MIT | 4 Oct 2026 |
| #19 | revdiff | TUI for reviewing diffs, files, and documents with inline annotations | 64/100 | ★ 929 | MIT | 14 Oct 2026 |
| #20 | claude-elixir-phoenix | Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with paralle… | 64/100 | ★ 566 | MIT | 14 Oct 2026 |
| #21 | herdr-reviewr | Review your coding agent's diff in a terminal pane and send line comments back to Claude Code, Codex, OpenCode or Pi. A herdr plugin. | 63/100 | ★ 887 | MIT | 10 Oct 2026 |
| #22 | claude-code-workflows | Development workflows for Claude Code that keep broad exploration focused on the outcome you approved. | 63/100 | ★ 695 | MIT | 13 Oct 2026 |
| #23 | claude-code-skills | Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explic… | 62/100 | ★ 577 | MIT | 12 Oct 2026 |
| #24 | agy-staff | Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code and OpenAI Codex. | 58/100 | ★ 741 | MIT | 7 Oct 2026 |
| #25 | shippie | extendable code review and QA agent 🚢 | 57/100 | ★ 2.5k | MIT | 28 Sept 2026 |
| #26 | mantis | A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities. | 46/100 | ★ 2.4k | Apache-2.0 | 14 Oct 2026 |
| #27 | skills | Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, C… | 40/100 | ★ 1.3k | MIT | 14 Oct 2026 |
| #28 | guard-skills | Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs | 36/100 | ★ 1.3k | MIT | 4 Jul 2026 |
| #29 | skills | Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof an… | 32/100 | ★ 1.3k | See repo | 4 Oct 2026 |
| #30 | Claude-Command-Suite | Professional slash commands for Claude Code that provide structured workflows for software development tasks including code review, feature creation, … | 24/100 | ★ 1.3k | See repo | 1 Mar 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Check which models and providers it supports.
- Prefer tools that show diffs and ask before running commands.
- Look for recent commits: coding agents change fast.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for agent skills →
Coding agents & IDE assistants
AI agent tools for developer tools →
Coding agents & IDE assistants
AI agent tools for the terminal →
Coding agents & IDE assistants
AI agent tools for macOS →
Coding agents & IDE assistants
AI agent tools for agent harnesses →
Coding agents & IDE assistants
AI agent tools for agent orchestration →
Coding agents & IDE assistants
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.