PR-Agent is an open source AI code review agent for development teams that want to choose where their reviewer runs and which model it uses. It reviews pull requests, writes descriptions, suggests code improvements, and answers questions about proposed changes. You can run it locally through a CLI, on a self-hosted server, in Docker, or through GitHub Actions.
It works with GitHub, GitLab, Bitbucket, Azure DevOps, and Gitea. Reviews can run automatically as part of a repository workflow, while developers can request feedback or ask questions through pull request comments. It can also find similar issues within a repository.
Model choice is flexible. PR-Agent connects to Ollama for local models and supports OpenAI GPT, Anthropic Claude, Google Gemini, DeepSeek, and Mistral through LiteLLM. Other supported services include Azure OpenAI, AWS Bedrock, Vertex AI, and OpenRouter. Hosting the agent yourself doesn't make cloud inference local: when you use OpenAI, review data goes to OpenAI's API.
Teams can adjust prompts, review categories, and review behavior to match their codebase. Its PR compression approach helps it process large changes, and the core review, improvement, and question-answering tools each use a single model call. PR-Agent is a community-maintained project originally developed by Qodo, separate from Qodo's hosted code review product. Its MIT license allows teams to modify the software and host it on their own infrastructure.
Claim this page and we'll verify you by hand. PR-Agent gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find PR-Agent?Promote it
Something wrong or outdated on this page?
89.6KUpdated 3 hours agoMIT
macOS · Windows · Linux · Docker#Agent Client Protocol#Git integration#Human approval
OpenHands is a coding agent platform for developers and teams that want agents to make changes across a codebase and handle recurring engineering work. You can run it on your own computer or self-host it on a server. Its core is open source under the MIT license, and a separate OpenHands Cloud service offers hosted execution.
4.8KUpdated 1 day ago
Docker · Web#Git integration#Human approval#LLM tracing
Agenta is an MIT-licensed, open source workspace for teams that want AI agents to handle tasks in chat and continue recurring work in the background. You can self-host it with Docker Compose or Helm to keep agents and workspace data on your infrastructure, or use Agenta Cloud as a hosted service.
3.7KUpdated 1 day agoMIT
Docker · Web · VS Code#Git integration#Hybrid search#llama.cpp backend
127.2KUpdated 24 hours agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Human approval
1.4KUpdated 1 day ago
Docker · Web#Git integration#Multi-user access#OpenAI-compatible API
Kodus is an AI code review tool for engineering teams that want automated pull request feedback while choosing where the reviewer runs and which model it uses. Its open source core uses the AGPL license and can be self-hosted with Docker Compose or on Kubernetes. Kodus also offers a hosted cloud service that manages the infrastructure.
2.4KUpdated 1 day agoApache-2.0
macOS · Windows · Linux#Agent Skills#Git integration#MCP
Twinny is an AI coding assistant for VS Code that lets developers choose where their models run: on their own computer, a private server or a hosted API. It's for individuals and teams who want code suggestions and repository chat with control over where their code goes. The extension and team gateway are open source under the MIT license.
Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.
ripwire helps AI coding agents find relevant code and assess changes without filling their context with whole files. It runs offline on your machine as a self-contained binary, with a CLI and an optional MCP server. It's for developers who want their agents to spend less context on repository research and check the effects of their edits.