Coding agents & developer tools
Code review agents
922 agents · most starred first
Code review agents, page 9 of 10
AI code/PR review agent. Fetches a pull request, asks an LLM to review it, posts inline comments + summary verdict back to the VCS. Self-hosted, multi-VCS (GitHub, GitLab, Bitbucket, Azure DevOps), multi-LLM (Anthropic / OpenAI / Google / Claude Code / Ollama). Standalone: no inter-package runtime deps.
Multi-agent code review system using LangGraph
Agent Skills code-review harness (Claude Code, Codex CLI): wiki-organised corpus of ~476 specialist reviewer leaves selected by semantic tree descent against the diff, aggregated into an 8-gate GO/NO-GO release verdict.
Multi-agent parallel code/spec review for OpenCode
Agentic code review skill and deterministic review tooling for AI-generated code.
Pragmatic .NET review skill pack for agentic development
Seatbelt — constitutional governance harness for agentic coding. The harness owns review timing and correction.
cubic uses AI to review code, speeding up PRs and catching bugs quickly.
AI-powered code review tool that works as a LangChain Tool, powered by Groq.
ESLint rules that catch the patterns LLM agents get wrong — and teach them to self-correct
AI-powered code review CLI for git changes
AI-powered code reviewer and autonomous developer agent
Multi-agent AI code review for git -- parallel agents with confidence scoring
AI Design Slop Index audit engine, schema, CLI, and agent adapters.
Make coding agents stronger engineering partners for reviews, implementation planning, and system design.
A multi-agent automated code review framework powered by LangGraph and Gemini.
Local-first verdict layer for AI coding-agent runs: graded repair receipts and a loop-gating exit code. No outbound network code; optional dashboard binds 127.0.0.1 only.
Multi-agent local code review powered by the Vercel AI SDK
AI pull-request reviewer: hybrid RAG + a code graph + Claude Code. Whole-repo context, inline GitHub comments grounded on exact code.
Generate reviewable safety evidence for AI-agent-generated pull requests.
Multi-agent coding council CLI for independent review and analysis
Audit repositories for AI agent readiness
Professional multi-agent codebase auditing and automated repair engine
CASP — the Coding-Agent State Protocol. The deterministic gate that validates your coding agent's project state against git and blocks the push the moment it drifts — across sessions, branches and a team. The complement to long-running autonomous models:
Local multi-agent council for code review, design decisions, and structured synthesis.
Security-first agentic code reviewer and best-practice auditor built on OpenCode.
Ship agentic. Stay coherent. Self-checking code integrity for AI coding agents, in the loop via MCP.
PassShore Agent — AI 代码质量本地守门人 / local AI code quality gatekeeper
Review functionality for Gaunt Sloth
A deterministic stop condition and code-graph context layer for AI coding agents: gives agents a code graph to make changes, then blocks only net-new detector-backed regressions at the stop boundary, with no model in the gate.
Scaffold PR review, security analysis, and multi-agent DAG starters on @open-multi-agent/core.
Deprecated: superseded by amicus (https://github.com/briandconnelly/amicus); 0.10.0 is the final release. Call Claude Code from Codex for bounded, independent code review and second opinions
Deprecated: superseded by amicus. Call OpenAI Codex from Claude Code for delegation, review, and second opinions
A full AI engineering team as plain Markdown files. 14 specialized agents for code quality, commits, reviews, security, and more — works with any agent runtime.
Custom OpenAI-powered GitHub PR reviewer that posts inline review comments and suggestions.
Core review engine for GHAGGA — AI-powered multi-agent code reviewer
Local-first review layer for coding agent sessions.
Agent IA d'audit technique de projets — analyse le code source et génère un rapport structuré en Markdown et PDF.
Portable hybrid code auditing + remediation orchestrators for arbitrary repositories.
Block any autonomous-agent PR from touching main until it provably passes spec + build + tests + checks.
Governed autonomy for any repo. An off-by-default autonomy loop that adopts your repo's rules, proposes small reviewable changes, and gates them in CI so weakened tests cannot merge.
The Codebase Immune System - Autonomous multi-agent governance for GitLab repositories
Agentic CLI to benchmark and audit repositories and review/resolve pull requests against industrial-grade standards.
Repository maintenance checks and diagnostics for AI-assisted Python development.
Static quality linter for AI agent skill definitions (SKILL.md files)
LLM-as-judge linter: enforce code-quality checks deterministic linters can't express, by driving real coding harnesses through oneharness.
Catch the LLM/AI calls you didn't need. A fast, deterministic linter that flags LLM API calls where plain code is simpler, cheaper, and more reliable.
Pragmatic, Gemini-powered AST Call-Graph AI Code Reviewer CLI
Guardrail checks for AI-agent-generated pull requests
AI-powered git diff analysis and code review with RAG context
AI agent scope enforcement for production codebases.
Architecture as Code for Vue & React — one config compiles into ESLint rules, a handbook, and an AI agent contract.
Local merge request review, step by step. Your AI agent reviews, codesema displays.
A local annotation tool for AI agent implementation plans.
The static analyzer your AI agent reads — finds production-blocking bugs in vibe-coded apps (CLI, GitHub Action, MCP server).
Rulvar determinism lint rules with structural JSON diagnostics for the planner self-repair loop.
`@pierre/diffs` is an open source diff and file rendering library that uses [Shiki](https://shiki.style/) with its JavaScript regex engine by default, with optional Shiki WebAssembly and Highlights backends. It's super customizable and packed with the fea
AI-powered pre-commit hooks for repo-specific code quality guardrails.
konsistent is a CLI tool that enforces structural conventions in TypeScript codebases.
Custom eslint rules for use within BluMint
Toolkit for building ESLint plugins in TypeScript — AST helpers, type utilities, rule-creation scaffolding, security benchmarks, and SARIF output.
Multi-agent PR review orchestrator CLI
Kyo-so: MCP-native, ACP-powered multi-agent review gates for AI coding workflows.
High-signal multi-agent pull request reviews for Pi
Deterministic commenter for agentic PR review — render, inline, post, adapt, cost, validate, print-schema
Deterministic triage of an AI agent's changes — see what it actually touched before you merge.
Stateful LangGraph workflow that reviews Git diffs with a reviewer-verifier loop and deterministic checks.
Checker and validator for the Barrage language — makes code readable by anyone
A local tool to understand what your coding agent changed and iterate on it fast. Like a pull request in your browser, where the agent answers instantly.
An MCP server that reviews your code the way a kernel maintainer would: bluntly, technically, without diplomacy.
A flake8 plugin that warns about expiring LLM model IDs
A local multi-agent code reviewer
A veto gate for AI-written code in LangChain / LangGraph — deterministic veto checks + a Claude Haiku 5.5 review. Free to try, no signup.
Two AI agent seats in one window: one builds, one reviews.
AI-powered code review from your terminal — security, performance, and quality agents on every PR
AI Developer Governance & Codebase Evaluator — A GraphRAG-powered multi-agent system featuring autonomous code evaluation, red-team testing, and dynamic LLM-narrated architectural documentation.
Semantic diff review for coding agents: an LLM turns a git diff into a narrative HTML report, a human comments on it, and the feedback comes back as plaintext.
Production-grade agentic code reviewer: multi-step LLM workflow with context retrieval, verification, and reproducible benchmarking.
Stops your coding agent from pushing unverified work. Your agent does the reviewing; a state machine records the result per-commit and gates the push.
Lint AI agent context files (AGENTS.md, CLAUDE.md) against the actual repository.
Agentic code analysis CLI for model-backed lint rules
Diff call stacks across git commits for agentic code review (23 languages)
Seal outcomes, verification, and decisions into an auditable workflow for agentic coding
The pure, no-I/O core of the AEG (Agentic Engineering Governance) engine.
Vinaya — Agentic Engineering Harness. Deterministic checks every AI coding agent must satisfy before merge.
Deterministic cross-language guardrails for agent-assisted development
Scheduled agent loops that audit a repository and the harness that judges it
<p align="center"> <h1 align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://pullfrog.com/frog-white-200px.png"> <img src="https://pullfrog.com/frog-green-200px.png" width="25px" align="center" alt="Green
Agent-Proof Mechanical Hard-Gate CLI for deterministic AI code governance
神治(Thearchy)— deterministic multi-agent quality governance for coding agents.
Measure how much of an AI coding agent's output is still in a git repo, and compare it to the humans on the same repo.
Automated AI Pull Request Reviewer & Security Code Auditor.
Evidence-backed project guidance and verification for coding agents
Deterministic audits of website readiness for agents.
An ESLint plugin that tries its best to prevent your coding agents from pooping your bed.
Audit HTML/CSS/JSX against WCAG 2.2 AA and produce a dated compliance report, or author/review accessible markup (native-HTML-first). A skills.sh agent skill: an install-free static engine (bundled, no npm install) plus the agent's judgment, with check/ve
Architecture authority for human and agentic software development — deterministic, evidence-backed enforcement of declared architecture.
The deterministic trust layer for autonomous AI coding agents. Compiler-grounded verification of what an agent actually did vs. what it claimed, blast radius mapping, and persistent contract memory.
CLI and agent skills for managing GitHub PR review comments. List, filter, reply, and watch for bot findings.
Glintbase Agent Harness — autonomous agent-readiness auditor (ARS 3.3, same engine as scan.glintbase.dev), Flight Simulator & CI drift shield