Self-Hosted AI Code Review Tools
PR-Agent and Kodus review pull requests and write their descriptions, while Repomix and Gitingest pack a repository into one prompt.
A desktop UI for parallel Claude Code agents on macOS, Windows and Linux, with isolated Git worktrees, code review and cost tracking.
52Updated 6 months ago
macOS#Agent Skills#Code execution#Git integration
ChatML is a desktop workspace for developers running several Claude Code tasks at once. It brings agent activity and code changes into one view so you can review work before merging it.
AI Code ReviewAutonomous Coding Agents+0
An Emacs AI assistant connects to Ollama and cloud APIs for chat, text editing and coding agents, with saved sessions and project context.
963Updated 1 month agoGPL-3.0
#Agent Skills#Code execution#Context compression
Ellama is an AI assistant for Emacs users who want help with writing and code inside their editor. It handles requests about selected text as well as longer conversations and coding tasks that need several steps.
AI Code ReviewAutonomous Coding AgentsCode Completion and IDE ExtensionsTranslationWriting and Email Assistants+0
A local or self-hosted coding agent workspace for Claude, Codex and OpenCode. Runs on your hardware; AI providers require your own subscription or API access.
1.4KUpdated 2 days agoApache-2.0
macOS · Windows · Linux · Docker · Web#Code execution#Git integration#Human approval
Jean is a desktop and self-hosted workspace for developers running coding agents across multiple projects. Repositories, terminals and git operations run on your computer or server, while the connected agents use your own subscriptions or API access. With Claude Code’s standard cloud connection, prompts and model responses go to its remote provider.
AI Code ReviewAutonomous Coding Agents+0
An open-source AI coding assistant for VS Code with local or hosted models, inline edits, code review and a self-hosted team gateway.
3.7KUpdated 2 days agoMIT
Docker · Web · VS Code#Git integration#Hybrid search#llama.cpp backend
Twinny is an AI coding assistant for developers who want completion and help with their repository inside VS Code, using models on their own hardware or a chosen server.
AI Code ReviewCode Completion and IDE ExtensionsLLM Gateways and Routers+0
AI code review CLI that runs locally, sends code to a configured LLM endpoint, and checks Git diffs or whole files. Apache 2.0 licensed.
50.6KUpdated 2 days agoApache-2.0
Windows · Web · JetBrains#Agent Skills#Batch processing#Git integration
OpenCodeReview is a locally installed AI code review CLI for developers who want findings tied to specific code lines. It sends code to a configured LLM endpoint through OpenAI- or Anthropic-compatible APIs. The local CLI handles the review process; model inference depends on that endpoint.
AI Code Review+0
A self-hosted AI coding agent workspace runs parallel tasks, mixes agents in pipelines and combines code review with an editor and terminal.
1.1KUpdated 22 hours agoAGPL-3.0
macOS · Windows · Linux · Docker · Web#Agent Client Protocol#Code execution#Distributed execution
KanDev is a self-hosted workspace for developers managing AI coding tasks and reviewing the resulting changes. It organizes work on kanban boards and lets you define workflows with your own agent choices and review gates.
AI Code ReviewAI Workflow AutomationAutonomous Coding Agents+0
An AI coding agent workflow for Kiro that combines written requirements, test-first development and independent validation under the MIT license.
258Updated 4 months agoMIT
#Agent Skills#Browser automation#Code execution
SpecShip is a workflow extension for Kiro that coordinates AI agents through planning, implementation, review and pull request preparation. It's for developers who want agent work checked against written requirements and tests.
AI Code ReviewAutonomous Coding AgentsMCP Servers and Agent Skills+0
A self-hosted AI agent workspace for teams, with Ollama support, shared files, scheduled tasks and approval controls.
4.9KUpdated 2 days ago
Docker · Web#Git integration#Human approval#LLM tracing
Agenta is an AI agent workspace for teams that want to delegate work and manage recurring tasks together. Agents plan their own steps, use connected tools and carry feedback into later work.
AI Bots for Chat AppsAI Code ReviewComputer and Browser Agents+0
Terminal coding assistant for local repositories on macOS, Windows and Linux. Use local models through Ollama or paid OpenAI access.
135.2KUpdated 19 hours agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Human approval
Codex CLI is a terminal coding assistant that works in your local repository on macOS, Windows and Linux. Developers can use it with models running locally through Ollama, including gpt-oss:120b, or connect to OpenAI through a paid ChatGPT account or API key. With OpenAI access, model requests go to the remote service even though file edits and commands run on your computer.
AI Code ReviewAutonomous Coding AgentsTerminal Coding Agents+0
A Pi extension that coordinates AI agents in resumable workflows, with reusable scripts, live inspection and headless runs.
253Updated 5 days ago
#Agent Skills#Code execution#Git integration
Pi Extensible Workflows is an extension for developers who want repeatable processes involving several AI agents. It coordinates resumable workflows inside the Pi host environment and lets you inspect work while it runs.
Agent FrameworksAI Code ReviewAI Workflow AutomationLLM Observability and TracingTerminal Coding Agents+0
A code context CLI and MCP server helps AI coding agents find relevant functions, trace callers and identify tests affected by edits.
2.5KUpdated 21 hours agoApache-2.0
macOS · Windows · Linux#Agent Skills#Git integration#MCP
ripwire helps AI coding agents find the code they need and check the effects of their edits. It's for developers who want agents to work with focused repository context instead of reading whole files.
Agent MemoryAI Code ReviewMCP Servers and Agent Skills+0
A self-hosted AI code review agent reviews pull requests, suggests improvements and answers questions, with local CLI and Docker deployment.
16.1KUpdated 22 hours agoMIT
Linux · Docker#Git integration#Ollama integration
PR-Agent is an open-source AI code review agent for development teams that want to run their own pull request reviewer. It can provide feedback automatically through repository workflows or respond to requests in pull request comments.
AI Code Review+0
Local AI code review software that checks commits with existing coding agents or models through Ollama and keeps review history on your machine.
1.8KUpdated 18 hours agoMIT
macOS · Windows · Linux · Web#Agent Client Protocol#Agent Skills#Code execution
roborev reviews commits in the background for developers working with AI coding agents. It brings findings back into active coding sessions so bugs can be addressed before a pull request.
AI Code Review+0
A local coding agent supervisor runs authenticated Claude Code agents with human design approvals, parallel Git worktrees and spending limits.
439Updated 5 months ago
Windows · Linux#Agent Skills#Code execution#Git integration
Foreman is a terminal app for developers who want to supervise Claude Code agents working in a repository. It takes feature requests through planning, design review and implementation, with human approval before agents begin the build.
AI Code ReviewAutonomous Coding AgentsTerminal Coding Agents+0
An AI coding agent orchestrator that uses Claude Code and Codex, with separate authors and reviewers and enforced merge gates.
418Updated 22 hours agoApache-2.0
macOS · Windows · Linux#Agent Skills#Code execution#Git integration
Liza coordinates AI coding agents for developers who want to delegate software work while keeping control over goals and constraints. It supports human-led pairing and multi-agent delivery runs that can proceed unattended.
Agent FrameworksAI Code ReviewAutonomous Coding AgentsTerminal Coding Agents+0
An open-source AI coding orchestrator that carries feature requests through planning, implementation, review and pull request publication.
127Updated 2 weeks agoApache-2.0
macOS · Linux#Code execution#Git integration#Human approval
Agentic Orchestrator coordinates coding agents for engineers supervising feature work across one or more repositories. It keeps requirements, design decisions and verification evidence attached to the work as it moves toward a reviewable pull request.
AI Code ReviewAutonomous Coding Agents+0
A local code intelligence tool that gives AI coding assistants focused review context through MCP, with change-impact analysis and an MIT license.
32.8KUpdated 2 days agoMIT
VS Code#Git integration#Knowledge graphs#MCP
Code Review Graph helps developers review changes with AI coding assistants without repeatedly supplying an entire repository. It keeps a local map of code relationships and returns the context relevant to a change or question.
Agent MemoryAI Code ReviewMCP Servers and Agent Skills+0
Self-hosted AI code review software that posts contextual pull request feedback and works with Claude, GPT, Gemini or self-hosted models.
1.6KUpdated 1 day ago
Docker · Web#Git integration#Multi-user access#OpenAI-compatible API
Kodus is an AI code reviewer for engineering teams that want automated pull request feedback and control over where the reviewer runs. Its reviewer, Kody, checks changes in the context of the surrounding code.
AI Code Review+0
An AI code review CLI that checks git changes with project context, using local Ollama models or cloud providers Gemini and OpenRouter.
42Updated 8 months agoMIT
macOS · Windows · Linux#Git integration#Ollama integration#RAG
CodeFox CLI reviews code changes for developers and teams who want feedback in the terminal or automated pull request checks. It considers the surrounding project code when assessing a git diff.
AI Code Review+0
LogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your projectLogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
