orchex
Utilizes OpenAI's LLM capabilities to plan, parallelize, and execute multi-file AI coding tasks.
Orchex Community
Describe what you want. Orchex plans, parallelizes, and executes — safely.
Community hub and Cursor plugin for Orchex — autopilot AI orchestration for multi-file coding tasks.
What is Orchex?
Orchex is an MCP server that orchestrates AI coding agents in parallel. Give it a task, and it auto-plans streams of work, executes them across waves with ownership enforcement (no file conflicts), and self-heals on failure. Supports 7 LLM providers with BYOK (Bring Your Own Key) and dynamic model discovery.
Related MCP server: Orchestrator MCP Server
Cursor Plugin
Install from Marketplace
Search for "Orchex" in the Cursor Marketplace, or visit cursor.com/marketplace.
Auto Setup
npx @wundam/orchex setupAuto-detects your IDE and writes the MCP config. Works with Cursor, Windsurf, Claude Code, and VS Code.
Manual Setup
Add to your Cursor MCP config (~/.cursor/mcp.json):
{
"mcpServers": {
"orchex": {
"command": "npx",
"args": ["-y", "@wundam/orchex"]
}
}
}Orchex auto-detects API keys from your shell environment (ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, DEEPSEEK_API_KEY). No env block needed.
Usage
Open Cursor and ask: "Build a REST API with authentication and tests"
Orchex generates a plan, shows you the streams, and executes on approval
Streams run in parallel waves — each stream owns its files, no conflicts
What's New
rc.32 — npm-to-beta + /mcp trust-boundary + reliability hotfix:
Hardened MCP transport authentication — unauthenticated cloud-server calls return a clear 401 with a sign-in CTA
Paid-tier signup unblocked —
/signup?plan=pro|teamnow reaches a working form instead of the invite-only dead endMore resilient cloud execution — orchex-cloud network hiccups surface as clear errors instead of silent hangs
Better visibility — config-overriding environment variables warn at startup; execution logs preserve history across runs
See the full release notes or visit the changelog.
Community
Use GitHub Discussions for:
Category | Purpose |
Announcements | Release notes, breaking changes |
Bug Reports | Issues you encounter during beta |
Feedback | Feature requests, UX suggestions |
Q&A | Setup help, troubleshooting |
Links
orchex.dev — Website & docs
@wundam/orchex on npm — Package
Integration guides — Claude Code, Cursor, Windsurf, and more
This server cannot be deployed
Maintenance
Related MCP Connectors
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
Build and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
The AI orchestration agent for modern software teams.
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
Related MCP Servers
- AlicenseAqualityDmaintenanceIntelligent LLM orchestrator that automatically routes tasks to the most appropriate AI model (Gemini, Qwen, Ollama, LM Studio) based on task characteristics, enabling distributed processing and parallel execution across local and network services.310 npmMIT
- AlicenseNot gradedqualityCmaintenanceCoordinates up to 64 parallel expert agents for complex multi-agent orchestration and intelligent task routing within Claude Code. It enables users to analyze requests, manage hierarchical execution plans, and monitor active orchestration sessions.MIT
- FlicenseNot gradedqualityNot gradedmaintenanceUniversal AI API Orchestrator. 850 tools across 53 services under a single MCP interface. Connect Claude, GPT, or Gemini to Stripe, Slack, GitHub, LinkedIn, Cloudflare, Shopify, Twilio, and 46 more via natural language. $0.10/execution, no subscription. Patent Pending.131 npm5-
- AlicenseAqualityDmaintenanceAI workflow orchestration platform with 100+ integrations, knowledge graph, and unified credits. Build, manage, and execute workflows from Claude Code, Cursor, or any MCP client.40279 npm3MIT