Skip to content
Agents tracked: 157 Downloads (7d): 216M up 9.6% GitHub stars: 4.2M VS Code installs: 145M Releases (7d): 233 Agent pull requests (last week): 940K Updated Oct 6, 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 (25.6M), Claude Code (14.8M), Augment Code (35.6K). By VS Code extension installs, the leaders are GitHub Copilot (78.6M), Claude Code (27.1M), OpenAI Codex (15.2M). By GitHub stars, the leaders are Claude Code (150K), OpenAI Codex (128K), Cursor (33.3K). The fastest grower over the last 30 days is OpenAI Codex, with downloads up 21%. As of Oct 6, 2026.

# Agent Category Pulse Downloads 7d 7d 30d VS Code installs Stars Latest release Price Last 90 days
1 Terminal 82 25.6M up 5.7% up 21.2% 15.2M 128K+153/day 0.160.1yesterday Free + $8/mo
3
Claude CodeAnthropic
Terminal 80 14.8M up 11.6% down 36.4% 27.1M 150K+161/day 2.1.290yesterday $20/mo
8
CursorAnysphere (owned by SpaceX)
IDEs 71 — — — — 33.3K+3/day — Free + $20/mo
9
GitHub CopilotGitHub (Microsoft)
IDEs 70 — — — 78.6M — — Free + $10/mo
31
DevinCognition
Cloud 53 — — — — — — $20/mo
98
Augment CodeAugment Code
IDEs 31 35.6K down 2.6% down 12.6% 780K 285 1.2.0-prerele…yesterday $20/mo

Ranks are overall positions by Pulse Score. Click a column to sort by what matters to you. Methodology.

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 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 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.