
Open-source AI coding agent for your terminal, IDE, and desktop
OpenCode is an open-source AI coding agent that helps developers write code directly from the terminal, IDE, or desktop. It comes with a built-in free model and also supports 75+ LLM providers via Models.dev, including Claude, GPT, and Gemini, so teams can match the model to their workflow and compliance needs.
The agent automatically loads the right language servers for LLMs, giving models accurate project context and language-specific intelligence. Its multi-session architecture lets you run multiple agents in parallel on the same project, while shared session links make collaboration and debugging simple. You can even sign in with GitHub Copilot or ChatGPT Plus/Pro to reuse existing subscriptions.
Built with a privacy-first design, OpenCode does not store your code or context data, making it suitable for sensitive environments. With a thriving open-source community and support for terminal, desktop, and IDE extensions, it is a practical coding companion for modern developers and engineering teams.
Software engineers, Open-source developers, Engineering teams, Indie developers, AI application builders
OpenCode is an open-source AI coding agent that helps developers write code in the terminal, IDE, or desktop, with support for many major LLM providers.
No. OpenCode includes a free built-in model, and you can also sign in with existing subscriptions like GitHub Copilot or ChatGPT Plus/Pro.
Yes. OpenCode offers a terminal UI, a desktop app, and IDE extensions, plus parallel sessions and shareable links.
No. It follows a privacy-first design and does not store your code or context data, making it suitable for sensitive environments.
Yes. OpenCode is an open-source project with an active community of contributors; you can inspect the source, contribute, and self-host.
VisActorFreeThe smart visualization suite within VisActor that automates chart creation and narrative-driven data storytelling across enterprise and BI scenarios.
Code ArenaFreeAn AI-powered code playground and LLM leaderboard that lets you build full-stack apps, games, and designs while comparing frontier models in real-time.
Visual Studio IntelliCodeFreeAI-driven code completion that lets Visual Studio developers focus on creation
TestDriverPaidAI code review and testing for GitHub — the AI code reviewer that actually runs your app.