Whitespace.
See who already built your idea — and the space they left open.

CLUSTER AGENT-CODE-REVIEW · 16 ENTRIES · EARLIEST ENTRY 2026-09-17

AI code review agents

This cluster consists of AI agents that automate code review on pull requests, with capabilities to learn from accepted and rejected feedback, enforce team rules, and post security or quality findings. The cluster's dated history is too thin to read a shape from—only one entry exists before the index start, so it predates the index or its members are undated. Traction leaders based on activity signal are reviewstage, DeepPr, and code-review-agent, though all currently show minimal star counts.

Entry timeline

ENTRY TIMELINE

JUN 2026: 1AUG 2026: 2SEP 2026: 12OCT 2026: 1
JUN 2026OCT 2026

Each bar is the month a member carries, which is a creation date where the source published one and a crawl date otherwise. Nothing in the index was found before 11 August 2026, and coverage broadened sharply on 14–15 August, so a bar from then on reports how much we found that month, not how much was built; an earlier bar reports how far back a member's own source dated it — not how long we have been watching.

Members by activity

Activity signals, not revenue.

Build origin · 1 ai-built · 15 unlabelled

Operator · 7 hobby · 2 indie · 1 commercial · 6 unlabelled

Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 16 listed below. Unlabelled means nothing has decided yet — not that the answer is small.

  1. 01codereviewagent3★15 days—AI assistant that learns from a team's past code reviews to provide personalized and context-aware code review feedback.
  2. 02DeepPr2★15 dayslivehobbyAI code review tool that analyzes pull requests with multiple agents and persistent memory to provide context-aware feedback.
  3. 03code-review-agent2★15 dayslivehobbyAI code review agent that learns from past accepted and dismissed review comments to enforce team-specific coding rules.
  4. 04magate1★2 dayslivehobbySecurity reviewer that inspects AI tool and API connection definitions for prompt injection, replacement, and excessive permissions, then issues allow, conditional-allow, or deny verdicts.
  5. 05jev-loop-detector1★19 dayslivecommercialWeb tool that detects loops in AI agent runs by grading each step as progressing, repeating, stuck, or needing escalation.
  6. 06docsifter1★23 daysliveindieLocal AI reviewer that checks technical documentation for language errors while preserving code, product names, and markup.
  7. 07modou-agent1★26 days—ai-builtLocal code review agent that verifies whether new code is genuinely covered by tests using reversible experiments.
  8. 08Technical-Assessment0★13 days—hobbyApplication that evaluates engineers' code-review skills by grading their review comments on flawed pull requests using AI.
  9. 09codesentinel-ai0★16 days—hobbyAI code review agent that analyzes pull requests, runs security and quality checks, and posts findings as comments with risk scores.
  10. 10ai-code-review0★27 days—hobbyAI agent that reviews code for vulnerabilities, generates patches, and posts remediation to pull requests.
  11. 11Sentinel2★1 moliveAI agent that analyzes dependency changes, validates them in isolation, and creates pull requests for review to keep developer projects up to date.
  12. 12deep-review0★1 mo—Multi-angle parallel code review tool for coding agents, providing ranked reports and adversarial verification.
  13. 13codelensAI0★1 moliveAI agent that reviews code changes and gives automated feedback to developers.
  14. 14AutoOps0★28 days—hobbyAI assistant that reviews code, detects bugs and vulnerabilities, monitors CI/CD pipelines, and posts feedback on GitHub pull requests.
  15. 15PRECEDENT0★27 daysliveAI code-review agent that reviews pull requests and learns from corrected mistakes to avoid repeating them in future reviews.
  16. 16ai-code-reviewer0★1 moliveindieAI-powered code reviewer that catches bugs, security issues, and suggests improvements with severity ratings, available as freemium SaaS.

Ranked by traction, highest first, and paged 20 at a time — this is a window on the cluster, never the whole of it. Ties are broken by a stable id so a product cannot appear on two pages or fall between them. Browse every cluster.