opencode
Terminal-based AI coding assistant featuring a themed native UI, automatic LSP integration, multi-agent sessions, 75+ supported LLMs, local and cloud model options, shareable debugging links, open source licensing, and session sharing for collaborative coding workflows.
Features
Properties
- Privacy focused
- Lightweight
- Support for Themes
Features
- No registration required
- Dark Mode
- No Tracking
- Command line interface
- Tui
- AI-Powered
Claude Integration- Local AI
opencode News & Activities
Recent News
Recent activities
- adri66 updated opencode
opencode information
Developed by
Anomaly Innovations Licensing
Open Source (MIT) and Free product.Written in
Rating
Average rating of 4.7Alternatives
93 alternatives listedSupported Languages
- English
AlternativeTo Categories
AI Tools & Services, Development, OS & UtilitiesGitHub repository
- 182,811 Stars
- 22,641 Forks
- 4753 Open Issues
- Updated
Featured in Lists
A list with 22 apps by justarandom without a description.
my software list, mostly open-source.I have used the vast majority of the software listed there myself for a long time.
A list with 10 apps by rainman without a description.
What is opencode?
OpenCode is a free, open-source AI coding assistant that helps you build, understand, and improve software projects. It works in the terminal, as a desktop app, and through IDE integrations, so you can use it in the environment that best fits your workflow.
Ask OpenCode to explain unfamiliar code, find bugs, generate features, refactor files, write tests, or help plan a larger change. It can use your project context and language-server information to give more relevant answers, while letting you run multiple AI sessions on the same project when needed.
You can connect OpenCode to a wide choice of AI models and providers, including Claude, GPT, Gemini, local models, GitHub Copilot. This gives you flexibility to choose the model, account, and cost that suit you instead of being tied to one provider.
OpenCode is designed with privacy in mind: it does not store your code or project context. You can also share a session through a link when you need help debugging, want to document a solution, or want to collaborate with someone else.
Whether you are learning to code, maintaining an existing project, or building software professionally, OpenCode provides a flexible AI-powered workspace for getting more done without leaving your development tools.
Comments and Reviews
Main thing is - OpenCode is powered by energized and very responsive team. They do care about all the github issues ppl are posting. This is incredible and rare nowadays to see the response to your issue within hours.
The product itself is just amazing FOSS alternative not only to Claude Code or OpenAI's Codex, but also to all the rest CLI AI agent coding tools:
With deep respect and love to all the talented folks in the dev team! You guys are driving changes forward.
LLMs has been around for 3 years already and only now we have a product that is really easy and fun to use to make things happen.
Globally, very solid agentic AI coding client, especially for people transititioning into FOSS from proprietary services like Github Copilot. For power users, a central problem is hardcoding. The system prompt in opencode cannot be easily modified. Although the system prompt is fine for vanilla use, for power users with lots of MCP servers offering tools superseding opencode defaults in efficiency and precision, the hard-coded system prompt is a real dragger, as AI models get confused from conflicting system and agent/user prompts on which tool to use.
A side note, the free models shipped with opencode are good for testing opencode out and working on simple personal projects. They are however unfit for production. Those models are heavily quantised, and the performances are way below the published benchmarks. Opencode could have made this clearer, but they don't want to, because currently their revenue depends wholely on opencode Go, a 10$/mo subscription offering model APIs at heavily discounted rates that they are trying to sell to every opencode user. Expectedly, the models are heavily quantised.