opencode

Name: opencode
Rating: 4.97 (31 reviews)

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

5.0•31 reviews•

873 followers

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

5.0•31 reviews•

873 followers

•

•

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.

Framer AI AgentsDesign and publish professional sites with AI

Promoted

opencode Launches

opencode zenAI models recommended for developers by the opencode team

Launched on September 29th, 2025

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

Launched on July 11th, 2025

5.0

Based on 31 reviews

Review opencode?

Reviewers describe opencode as a fast, responsive terminal coding agent with a clean TUI, strong customization, and unusually flexible model choice. Users especially like avoiding extra platform fees, extending it with custom commands, and using it smoothly in the terminal, while one notes editor integration also works well. Founders of Edgee, Polygraph, and Vokal reinforce its value as a compatible, developer-friendly runtime that fits existing tools and shared workflows. Reported drawbacks are limited: local model setup could be simpler, and one reviewer says large-codebase navigation and control safeguards may need more polish.

+28

Summarized with AI

Reviews

All Reviews

Most Informative

•1 review

What's great

OpenCode is an absolute lifesaver. Paying a platform subscription fee on top of your own model API costs is such a hassle, and this tool completely solves it. It runs incredibly well, it's open-source, and it's highly customizable. The command system is robust, and it's super easy to develop or plug in custom extensions. I'm definitely not switching to anything else—I could honestly talk about how good it is all day!

What needs improvement

The main thing I would improve is making it easier and more seamless to set up and run local models. Simplifying that specific process would make this tool absolutely flawless.

vs Alternatives

I looked into several mainstream alternative solutions, but most of them force you into rigid ecosystem subscriptions where you end up paying double: once for the platform itself and then again for the actual AI model tokens/APIs you consume. I chose OpenCode because it completely eliminates that middleman fee while giving me full open-source freedom.

Ratings

Ease of use

Reliability

Value for money

Customization

Report

26 views16d ago

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

111 views3mo 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

149 views10mo ago

•1 review

What's great

What needs improvement

The main thing I would improve is making it easier and more seamless to set up and run local models. Simplifying that specific process would make this tool absolutely flawless.

vs Alternatives

Ratings

Ease of use

Reliability

Value for money

Customization

Report

26 views16d ago

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

111 views3mo ago

•1 review

Report

149 views10mo ago