Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

AI code review agents

Agents that read your pull requests, comment on bugs and risky changes, and in some cases fix what they flag.

By weekly package downloads, the leaders are OpenAI Codex (26.6M), Claude Code (18.9M). By VS Code extension installs, the leaders are GitHub Copilot (79.4M), Claude Code (30.6M), OpenAI Codex (16.9M). By GitHub stars, the leaders are Claude Code (156K), OpenAI Codex (136K), Cursor (33.3K). Among agents with at least 20,000 downloads in the last 30 days, the fastest grower is Augment Code, with downloads up 33%. As of Nov 20, 2026.

Works with:
Usage
  1. 1
    Anthropic · Terminal · terminal agent + IDE extensions

    Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, with VS Code and JetBrains integrations plus desktop, web and mobile access. It runs Claude models through a Claude subscription, an Anthropic Console API key or supported third-party cloud providers.

    CLIIDEDesktop appMCPOwn API keyPlan limits
    88 18.9M up 15.5% 156K yesterday 18.9M downloads a week up 15.5% 30dGid 88 $20/mo
  2. 2
    OpenAI · Terminal · terminal agent + IDE extension + cloud agent

    OpenAI's coding agent, offered as an open-source terminal CLI, an IDE extension, a desktop app and a cloud agent that works on repositories. Users sign in with a ChatGPT account or use an OpenAI API key; with an API key, Codex works in the CLI, SDK and IDE extension without cloud features such as GitHub code review and Slack. On the Free and Go plans Codex runs in the desktop app (subject to rollout); the web, CLI and IDE extension come with Plus and higher.

    Open sourceCLIIDEDesktop appMCPLocal modelsOwn API keyPlan limits
    84 26.6M up 7.4% 136K 7d ago 26.6M downloads a week up 7.4% 30dGid 84 Free + $8/mo
  3. 5
    GitHub · IDEs · AI coding assistant (IDE agent mode, CLI and cloud agent)

    AI coding assistant from GitHub offering completions, chat and agent mode in IDEs, a terminal CLI, a desktop app and a cloud agent that works on assigned tasks in the background and opens pull requests. Models from several providers can be selected.

    IDECLIWeb appMCPLocal modelsOwn API keyPlan limits
    75 — — — — 79.4M VS Code installsGid 75 Free + $10/mo
  4. 6
    Anysphere · IDEs · AI IDE

    AI coding editor and agent platform with a desktop app, a CLI, web and mobile agents, and cloud agents that run tasks in remote environments. It offers models from OpenAI, Anthropic, Google, SpaceXAI (Grok) and Meta alongside its own Composer models.

    IDECLIWeb appMCPOwn API keyPlan limits
    73 — — 33.3K — 33.3K GitHub starsGid 73 Free + $8/mo
  5. 24
    Cognition · Cloud · cloud coding agent

    Autonomous AI software engineer from Cognition that runs in cloud VMs, takes work from Slack, Teams, Linear, Jira or an API, and delivers pull requests. Devin Desktop and the Devin CLI act as local companions to the cloud agent; the CLI can also create, steer and resume Devin Cloud sessions.

    Web appCLIDesktop appMCP
    56 — — — — 1,322 Homebrew installs a monthGid 56 $20/mo
  6. 117
    Augment Code · IDEs · AI coding agent (IDE plugin, CLI, cloud agents)

    AI coding platform built around a codebase Context Engine, delivered as VS Code and JetBrains extensions, the Auggie CLI and Cosmos, a platform for always-on cloud agents and software-delivery workflows.

    IDECLIMCP
    36 54.3K up 33.0% 293 2d ago 54.3K downloads a week up 33.0% 30dGid 36 $20/mo

“#” is the position among products of the same kind (agents, frameworks, tooling) by Gid Score, our 0–100 composite of adoption, community, attention and momentum. Use the filters and sorting above, or switch to the table view. Methodology · All AI agents.

What AI review is good for

Review agents catch a useful share of bugs, missing edge cases and inconsistencies before a human looks, and they never get tired of large diffs. They are weaker at judging whether a change is the right design. Most teams use them as a first pass that a person then reviews, not as a replacement for approval.

What each agent does for this task

Only agents whose own documentation describes this use are listed. Checked Oct 6, 2026.

Agent What it does Source
GitHub Copilot Copilot code review comments on pull requests and can be set to review automatically docs
Claude Code Code Review (Team and Enterprise plans, GitHub repositories) and GitHub Actions run Claude on pull requests docs
OpenAI Codex Reviews GitHub pull requests when enabled or mentioned docs
Cursor Bugbot reviews pull requests for bugs and leaves comments on GitHub, GitLab, Bitbucket and Azure DevOps docs
Devin Devin Review analyses pull requests and can fix the bugs it flags docs
Augment Code Augment Code Review posts review comments on pull requests docs

Setting one up

  • Start on one repository and tune what it comments on, or it will be noisy.
  • Decide who can trigger fixes. Some agents can push commits to the branch; keep that behind an explicit request.
  • Compare on your own PRs. Run two agents on the same pull requests for a week and count useful comments.

More options by job: the best AI agents in every category.