Free AI code review tools (2026)
AI code review tools that you can use without paying: open-source projects plus tools with a free plan. Here are the top 25 of 33 from the AgentScout directory.
Quick answer: the top picks on this list, ranked by GitHub stars and listing maturity, are CLI-Anything, Open Code Review and GitHub MCP Server, out of 25 tools listed below. At a glance: 21 open-source, 24 free or freemium and 21 local or self-hosted across 25 link-checked tools (last verified ).
Verified on : every tool link on this page was checked by our daily link check. No paid placements.
Ranked comparison (top 10)
| # | Tool | Pricing | Best for | Open source | Runs locally | GitHub stars |
|---|---|---|---|---|---|---|
| 1 | Open source | write code, control a computer | Yes | Self-hosted | 57,786 | |
| 2 | Open source | write code, research the web | Yes | Self-hosted | 49,071 | |
| 3 | Open source | write code, connect tools via MCP | Yes | Self-hosted | 34,082 | |
| 4 | Freemium | write code | No | 13,706 | ||
| 5 | Open source | write code, run code safely | Yes | Self-hosted | 11,146 | |
| 6 | Open source | write code | Yes | Self-hosted | 6,120 | |
| 7 | Open source + cloud | write code, build an agent | Yes | Self-hosted | 3,246 | |
| 8 | Open source | write code | Yes | Self-hosted | 2,514 | |
| 9 | Open source | write code, make diagrams | Yes | Offline | 2,298 | |
| 10 | Open source | write code, automate the browser | Yes | Self-hosted | 2,282 |
Updated
How we picked and ranked: tools are matched by category, the pricing each maker states and what each tool says it does. They are ranked by GitHub stars as recorded on each listing (link checks 2026-11-15); tools without a tracked repo follow, by listing maturity. No paid placements.

1. CLI-Anything
CLI-Anything, from the HKU Data Science lab (HKUDS), is an Apache-2.0 project that turns existing desktop software, codebases and web APIs into agent-native command-line tools, so coding agents like Claude Code can drive programs such as Blender, GIMP, LibreOffice or CAD apps through structured commands with previews instead of screenshots. Its CLI-Hub (pip install cli-anything-hub) lets agents browse and install community-built CLIs, and contributors can add new harnesses by pull request.
Pricing (as stated): Open source (Apache-2.0) · Active

2. Open Code Review
Open Code Review is Alibaba's Apache-2.0 AI code review CLI (ocr), used internally by tens of thousands of Alibaba developers before it was open-sourced. It reads Git diffs and sends changed files to an agent that can read whole files, search the codebase and inspect related changes, then posts structured line-level comments; deterministic pipelines and a built-in multi-language ruleset catch issues like null-pointer risks, thread safety, XSS and SQL injection, and ocr scan reviews whole files or folders without a diff. It works with any OpenAI- or Anthropic-compatible model endpoint.
Pricing (as stated): Open source · Mature

3. GitHub MCP Server
GitHub's official MCP server for letting agents work with repositories, issues, pull requests and Actions.
Pricing (as stated): Open source · Mature

4. Qodo
AI code review and testing agents that work in the IDE, the terminal and pull requests to catch issues before merge.
Pricing (as stated): Freemium · Mature

5. Open SWE
LangChain's asynchronous coding agent that takes work from GitHub issues, Slack or Linear, implements it in an isolated sandbox and opens a pull request.
Pricing (as stated): Open source · Mature

6. Emdash
A free, open-source agentic development environment (YC W26) for running Claude Code, Codex and other coding agents in parallel, each in its own worktree, then reviewing diffs, PRs and CI in one place.
Pricing (as stated): Free and open source (Apache-2.0). · Mature

7. Redamon
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what.
Pricing (as stated): Open source + cloud · Active

8. Shippie
Extendable code review and QA agent that reads your diff, explores the codebase and posts focused review comments.
Pricing (as stated): Open source · Active

9. PR Lens
PR Lens helps people review code that agents wrote. For each pull request it draws animated architecture and data-flow diagrams inside the PR, showing which parts of the app were added, changed or removed, what else depends on the change and how a request now moves through the system. It also flags likely bugs, security holes and design problems in the same review comment, with a ready prompt to hand each fix to your coding agent or an autofix. The open-source core runs locally and installs as an agent skill.
Pricing (as stated): Open-source core (MIT), runs locally; installs as an agent skill · Active

10. Sheprd
Sheprd is an Apache-2.0 native workspace for terminals and AI coding agents on macOS, Linux and Windows, built in Rust with GPUI. It organises repositories, Git worktrees, tabs and splits, lets you chat with agents, review their changes and track pull requests and usage across local, SSH and cloud machines, and adds browser previews, automations and phone remote control on top of a Herdr terminal daemon.
Pricing (as stated): Open source · Active

11. Kodus
Self-hostable AI code reviewer for GitHub, GitLab, Bitbucket and Azure DevOps pull requests that works with the model you choose.
Pricing (as stated): Open source + cloud · Active

12. Superlog
Superlog runs AI agents on routine engineering work around production. You set up automations with triggers and connectors, for example rating each new Sentry issue, posting a plain-language summary to Slack and opening a pull request with the fix, comparing error rates and latency against their normal range every hour, adding missing logs and spans to hard-to-debug code paths, or answering community questions from your code and docs. You choose the model and agent harness and bring your own tokens or subscriptions. The core is open source (Apache-2.0) with a hosted version.
Pricing (as stated): Open source (Apache-2.0) to self-host; hosted plans and enterprise on the pricing page; bring your own model tokens or subscriptions · Active

13. Tracely
Tracely is open-source, trace-native CI/CD for AI agents: it grades every production trace with evaluators, clusters failures into issues, freezes bad runs into replayable test cases and blocks pull requests that would reintroduce them.
Pricing (as stated): Self-host free (MIT); hosted Free $0 (20k traces/month), Team $49/mo; LLM judges run on your own OpenRouter key · Active

14. OpenQodex
Code review that runs inside your coding agent before you push, combining security and quality scanners with a separate AI reviewer.
Pricing (as stated): Open source · Active

15. LoopForge
LoopForge is Tencent's self-hosted, MIT-licensed workspace for shipping software with coding agents: you describe a requirement to its Main Bot in chat, and it opens a Docker sandbox, checks out your repositories, delegates to project roles and opens the pull request. Proven ways of working are saved as SOPs that combine agents, scripts and human approval gates, and it drives CLIs such as CodeBuddy, Codex, Claude Code, OpenCode and Cursor CLI.
Pricing (as stated): Open source · Active

16. Aletheore
Aletheore audits code repositories and backs every finding with evidence. Its deterministic scanner looks for leaked secrets, vulnerable dependencies and dead code, it can watch live endpoints and draw architecture maps, and it reviews pull requests automatically through a GitHub Action. A built-in MCP server lets coding agents run the same audits.
Pricing (as stated): Open source + cloud · Active

17. CodeAF
CodeAF is an open-source software factory from AgentField built to run on open models. It ships ready-made specialist agents you call with slash commands, one to build features like a senior developer, one to audit code for security issues and one to review GitHub pull requests, and spreads the work across a pool of models to balance cost and quality.
Pricing (as stated): Open source · Active

18. OpenComputer
OpenComputer is a platform for building and deploying long-running AI agents as code. You define an agent as a TypeScript function with its model, tools and MCP servers, deploy it with one command, and every session gets its own real cloud computer, with managed sessions, schedules and API keys kept outside the agent's runtime. Templates include a coding agent that edits a repo, runs checks and opens a draft pull request, and market-research and GTM agents; its own Slack coding agent runs on it. Pricing is pay-as-you-go for model calls and per-second machine time.
Pricing (as stated): Pay as you go (model calls at API rates, machine time per second, $10 free credit); Pro $20/mo and Max $200/mo prepaid credit at 10x; Enterprise custom. Core is open source (Apache-2.0) · Active

19. GitKraken MCP
GitKraken's MCP server, via the GitKraken CLI, for managing repos, pull requests and issues across GitHub, GitLab and Bitbucket.
Pricing (as stated): Community plan free (OSS); paid plans with 14-day trial · No recent updates (last commit Jun 2025)

20. Mira
Mira is an open-source agent project that helps builders handle AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs.
Pricing (as stated): Open source · Active

21. Muxin
Muxin is a free, open-source desktop app that puts all your Macs, Linux, Windows and cloud machines in one window, so you can run Claude Code, Codex and other agent CLIs on any of them, see their screens and logs, and take changes to a pull request.
Pricing (as stated): Free and open source (Apache-2.0) · Active

22. Roomote
Cloud coding agent from the Roo Code team that runs your real dev environment, verifies its work, reviews code with a second model and hands back PRs with live previews; works from Slack, Teams, GitHub and Linear, self-hosted or on its cloud.
Pricing (as stated): Self-host free up to 10 users; Roomote Cloud from $49/mo after a 7-day trial; bring your own model key · Active

23. Orbi
Orbi is an open-source (AGPL-3.0) software factory for GitHub repositories. When you label a GitHub Issue ai-ready, Orbi implements it in an isolated worktree, opens and reviews pull requests in a separate AI review session that checks acceptance criteria and repairs failing tests, merges the exact reviewed commit SHA, and cuts a tagged GitHub Release when a human applies the ai-release label.
Pricing (as stated): Self-hosted: free and open source (AGPL-3.0 or Sustainable Use License, bring your own model); Cloud: 3 free merged deliveries (no card), Solo $24/month (400M tokens, 1 repo), Pro $66/month (1.2B tokens, 5 repos) · Active

24. Trace Mcp
Trace Mcp is an MCP server that gives agents a way to handle code graph MCP: 81 languages, 91 frameworks, 72.7% fewer PR-review tokens, comprehension.
Pricing (as stated): Open source · Active

25. Diffinery
Open source, agent-first GitHub alternative on your own Cloudflare account: git hosting, pull requests, Actions-compatible CI, and agents with their own accounts.
Pricing (as stated): Apache-2.0, free to self-host on your own Cloudflare account; hosted early access · Active
FAQ
What are the best free AI code review tools?
Ranked by tracked GitHub stars, the top free AI code review tools in our directory are CLI-Anything, Open Code Review, GitHub MCP Server, Qodo, Open SWE. Stars measure popularity, not fit, so compare a few against your own task.
How many free AI code review tools does AgentScout list?
33 tools match. This page shows the top 25. Pricing mix on this page: Open source (15), Open source + cloud (6), Freemium (3), Usage-based (1).
Are these tools really free?
Pricing is what each maker states on their site. Open-source tools are free to self-host but may need a paid model API key or offer paid cloud plans; freemium tools have a free plan with limits. Check each official site.
Where can I see every tool for reviewing pull requests?
Our task page lists all 43 tools we match to reviewing pull requests.
Related
- All tools for reviewing pull requests
- coding (19)
- MCP servers (5)
- QA & testing (2)
- security & governance (2)
By role: For developers · For QA engineers
Best-of lists
Related categories
Facts come from our directory listings; pricing is as each maker states it and can change. Check official sites before you choose.