Desktop and web interface for OpenCode AI agent

OpenCode 中文实战课源码与内容仓库：一课一页，覆盖入门到实战工作流。

Run coding agents in isolated Incus containers (sandboxes) with session persistence, workspace isolation, and multi-slot support.

'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and other APIs running on your Mac through a single aggregated OpenAI-compatible API endpoint. Supports Apple Vision and single command (non-server) inference with piping as well . Now with Web Browser and local AI API aggregator

A MCP server for Django applications, inspired by Laravel Boost.

Vercel AI SDK community provider for OpenCode SDK - Use OpenCode configured providers via SDK

Collects CLAUDE.md files from directory hierarchy (project folder up to `~/.claude/`), embeds their `@`-imports and commands, and generates processed context files that can then be used as context with other agents.

A collection of AI Skills specialized in Django Backend development

A configurable personality and mood system plugin for OpenCode

Superpowers for Everyone, Agent Agnostic Skills, not just Claude Code, but supporting tools for GitHub Copilot, OpenCode, Gemini, Cursor, etc.

Provide a secure, rootless, sandboxed Ubuntu/Linux environment on Android with a Termux-like interface but stronger isolation and control.

A collection of agents, sub-agents, commands, and skills (using openskills) to enhance an opencode agent's ability to work with GitHub

🤖 Define and execute task-specific AI agents in markdown across various platforms with the Sub-Agents Skills for seamless integration and portability.

A TUI application to list opencode.ai sessions and view or open them

MCP server for OpenCode AI — 70 tools, 10 resources, 5 prompts. Use npx opencode-mcp with Claude Desktop, Claude Code, Cursor, Windsurf, or any MCP client.

SuperCode Framework inspired by SuperClaude for Opencode.ai

OpenCode AI 助手配置项目，支持 Google Gemini、Anthropic Claude、智谱 GLM、小米 Mimo 等 7+ 个 AI 模型。提供智能 Git 提交工作流、跨平台环境适配（NixOS/Windows/Debian/CentOS）和 MCP 协议集成，提升 AI 辅助开发效率。

⏺ A benchmark harness for evaluating coding agents (LLM-powered CLI tools) across synthetic software engineering tasks. Compares correctness, speed, and token efficiency across multiple languages and task categories including bugfixes, features, refactors, and scratch implementations.

A lightweight CLI to install, pin, and enable agent skills across projects with a single local store and per‑agent symlinks.