Coding agents & developer tools

Code review agents

922 agents · most starred first

Code review agents, page 10 of 10

agent-review-roundtable

Open-source multi-agent roundtable code review engine (CLI-first).

dsh-command-code-review

/code-review slash command for DeepSeek Harness — multi-agent review of pull requests and local code, with configurable confidence scoring

agentic-crap-py

Function-level CRAP analysis for Python using LCOV coverage.

langgraph-lint

Find LangGraph wiring bugs before they become a runtime KeyError.

pr-review-agent

Locally-hosted LLM-based PR review agent with enforced usage budgets

@tequila99/githuman

Review AI agent code changes before commit — Vue edition

p-backlog

Keep pull requests clean and audit findings safe: a local, autonomous backlog for Claude Code. The agent files out-of-scope issues as Markdown tasks with context and re-checks them as code changes. Optional web UI with metrics.

signoff-ui

Review what your agent changed and approve what it may do: React components for multi-file diff review and tool approvals that return a result your agent acts on, for AI SDK 6 & 7, AG-UI and ACP agents, inside assistant-ui, AI Elements or your own chat.

dsh-review

Packaged multi-agent adversarial code review for DeepSeek Harness — one finder per lens in parallel, then a verifier per finding whose task is to refute it, so only confirmed defects are reported.

ultracite

The linter and formatter for agentic development.

agentic-retro

agentic-retrospective: reviews finished agent coding sessions and proposes improvements

@odeloic/review

Agentic coding review tool.

@bleedingdev/ultracite

The linter and formatter for agentic development.

agentvow

Check a coding agent's claims against the repository before you approve.

apimirage

Catch hallucinated and deprecated API usage: AST scan plus real importlib existence checks

pragmatic-audit

Audit a repository against The Pragmatic Programmer, and give agents a practical standard to code by.

@agentlintel/cli

Deterministic architecture gate for AI-agent codebases: verified facts, enforceable rules, conformance fixtures, write-boundary guard.

vibe-gate-mcp

Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock

agent-code-review

An open-source multi-agent code review framework for AI coding agents.

agent-comment-lint

Stops AI coding agents from bloating code comments. Zero dependencies.

agentguard-sentry

GitHub Action that detects authorization and tenant-isolation regressions in Python/Django pull requests

agentguards

GitHub Action that detects authorization and tenant-isolation regressions in Python/Django pull requests

More in Coding agents & developer tools