Orchex — Autopilot AI Orchestration — orchex

# Orchex > Describe what you want. Orchex plans, parallelizes, and executes — safely. Orchex is a multi-LLM orchestration tool. It takes a natural language description of what you want to build, generates an execution plan with parallel streams, and coordinates multiple LLM providers to execute it — with ownership enforcement, self-healing, and learning. ## Key Features - 6 LLM providers: Claude, OpenAI, Gemini, DeepSeek, Ollama, AWS Bedrock - Automatic plan generation from natural language - Parallel stream execution with dependency management - File ownership enforcement (no merge conflicts) - Self-healing: automatic error detection and fix stream generation - Dynamic model registry: auto-discovers available models from providers daily - Learning system: improves across executions ## MCP Tools 12 tools available via MCP: init, add_stream, status, execute, complete, recover, learn, init-plan, auto, reset-learning, rollback-stream, reload ## Quick Setup Auto-configure Orchex for your IDE: ``` npx @wundam/orchex setup ``` Or manually add to your MCP config: ```json { "mcpServers": { "orchex": { "command": "npx", "args": ["-y", "@wundam/orchex"] } } } ``` ## Links - Documentation: https://orchex.dev/docs - Pricing: https://orchex.dev/pricing - npm: https://www.npmjs.com/package/@wundam/orchex - MCP Registry: io.github.wundam/orchex