Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.
Powerful AI Client
💡 Turn experience into repeatable execution.
The ultimate CC proxy
Build resilient agents.
Windows Codex Desktop multi-account via AuthSwap. Shared workspace, separate ChatGPT logins.
Self-hosted MCP server for your documentation
The most RAM efficient harness
Deterministic prose checks for clearer coding-agent responses
Qt C++ library for working with AI/LLM Providers and MCP
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors
A local sandbox for your AI agents
A fast codebase indexer and knowledge wiki for AI agents.
MCP Server for Text to Speech
The agent that grows with you
A MCP server allowing LLM agents to easily connect and retrieve data from any database
An MCP server that provides LLMs access to other LLMs
An MCP server that scales development into controllable agentic, recursive flows, and build a feature from bottom-up
Token usage tracker for (not only) OpenCode
A native (really fast!!) cross-platform client for OpenCode
Shell and coding agent on mcp clients
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
An MCP Multimodal AI Agent with eyes and ears!
Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy