opencode

Your terminal's AI agent, with any model you want

5.0•21 reviews•

744 followers

Your terminal's AI agent, with any model you want

5.0•21 reviews•

744 followers

Visit website

AI Code Editors

opencode is an open-source AI coding agent built for the terminal. It features a native TUI, multi-session support, and is model-agnostic, letting you use Claude, OpenAI, Google, or even local models.

opencode Reviews

The community submitted 21 reviews to tell us what they like about opencode, what opencode can do better, and more.

5.0

Based on 21 reviews

Review opencode?

Reviewers describe opencode as a fast, clean terminal coding agent with a strong TUI, responsive behavior, and unusual flexibility in letting teams switch models for different jobs. Users say setup is simple and the tool feels helpful without getting in the way; one also notes editor integration with VS Code, Cursor, and Windsurf. Makers of YepCode, CoChat, and Cosyra say it is solid enough to build products on, praising reduced ops friction, UI, and community. Criticism is limited but points to newer-tool rough edges, especially around large-codebase navigation and safety controls.

+18

Summarized with AI

AppSignalGet the APM insights you need without enterprise price tags.

Productivity•Analytics•Developer Tools

Reviews

All Reviews

Most Informative

Athena

•1 review

What's great

Model-agnostic design is a strong differentiator, being able to swap between Claude, OpenAI, Gemini, or local models without lock-in is genuinely useful
Native TUI feels right for a terminal tool; it respects the environment it lives in rather than fighting it
Multi-session support is a practical win for developers juggling multiple contexts
Open-source means the community can audit, extend, and self-host it

What needs improvement

The tool is still relatively new, so context window management and large codebase

navigation likely need more polish

No mention of agentic loop controls (e.g., approval modes, auto-apply guardrails) trust and safety mechanisms matter a lot for an agent that writes code
Terminal-first UX limits accessibility; there's no IDE extension path mentioned, which narrows the audience
"Model-agnostic" is only as strong as the abstraction layer, if switching models silently degrades quality (e.g., tool-use inconsistencies), users may not notice until it's a problem

Ratings

Ease of use

Reliability

Value for money

Customization

Report

27 views24d ago

used opencode to build Zyphe

•7 reviews

Opencode is where the code gets written now. Features, refactors, debugging weird issues. We run it with Claude on the hard stuff and switch to something cheaper for boring work like renaming files or cleaning up imports. Same setup, whatever model we want.

Alternatives Considered

Report

3 views4d ago

used opencode to build Ajelix AI Agent for Work

•2 reviews

One of the best open source coding tools available that allows for iteration on different concepts and ideas fast, without vendor lock-in.

Alternatives Considered

Report

2 views4d ago

•1 review

I’ve just tried out opencodes zen recently, it’s one of the simplest and fastest setups I’ve come across in a while, for working with LLMs in the terminal. The "TUI" feels super clean and intuitive, no fussing around, just install, configure and start using it. (waiting for its support on the Bun runtime though)

Report

98 views7mo ago

•8 reviews

opencode now integrates with vscode, cursor, windsurf, etc it'll be aware of what file you're in and you can easily send inject selected lines into the prompt start opencode inside your editor and it'll install the extension

Report

63 views10mo ago

•5 reviews

Tried opencode and it seems to be super responsive and smart without being intrusive. I love that I can plug in any model I want. It actually feels like coding with a helpful partner in the terminal.

Report

37 views10mo ago

used opencode to build YepCode

•5 reviews

Opencode is one of the main pieces of our YepAgent. We start one instance in one of our sandboxes, and it may help with all the user's base source code to help them to build YepCode processes. You can see the full making of in this blog post: https://yepcode.io/blog/yep-agen...