Archestra.AI Open Source AI Platform

<div align="center"> <img alt="GitHub commit activity" src="https://img.shields.io/github/commit-activity/m/archestra-ai/archestra"/> <img alt="Github Last Commit" src="https://img.shields.io/github/last-commit/archestra-ai/archestra"/> [](https://github.com/archestra-ai/archestra/graphs/contributors) <p align="center"> <a href="https://www.archestra.ai/docs/platform-quickstart">Getting Started</a> - <a href="https://github.com/archestra-ai/archestra/releases">Releases</a> - <a href="https://archestra.ai/join-slack">Slack Community</a> </p> </div>

All-in-one enterprise AI platform for those who are tired of wiring up kagent, kMCP, OpenWebUI, and LiteLLM — and still being frustrated by reliability, governance, security, observability, cost tracking, and the general complexity of building a mature enterprise AI platform.

• 💬 Internal chat UI for non-technical users
  • 👥 Projects for collaboration
  • 📱 MCP Apps
  • 💼 Slack, MS Teams, and Email UIs
• 🛠️ Developer LLM & MCP access portal (Claude, Codex, etc.)
• 🚪 LLM Gateway
  • 🌐 Any provider (Anthropic, OpenAI, Azure, Bedrock, DeepSeek, and more)
  • 💰 Cost management
  • 🔑 Virtual API Keys
  • 🎯 Dynamic model optimization
• 🔌 MCP Gateway
  • 🪪 OAuth & On-Behalf-Of (OBO) for user-delegated MCP access
• 🤝 A2A Gateway
• 📦 Private MCP Registry
• 🎼 MCP Orchestrator
  • ☸️ Kubernetes operator
  • 🚀 Self-serve promotion mechanism and governance
• 🤖 Agent Runtime
  • ⏰ Scheduled, Email, and Webhook (A2A) triggers
  • 🧬 Sub-agent delegation
  • 🧠 Reusable Agent Skills
  • ⚡ Sandboxed, blazing-fast code execution
  • 📁 K8S-native filesystem
• 📚 RAG Knowledge Base
  • 🔗 Knowledge Connectors for external sources
• 🧩 Mini app builder
• 🛡️ Deterministic Guardrails
  • 🧪 Dual LLM and Lethal Trifecta protections
• 🪪 Identity & Access
  • 🔐 SSO (OIDC, SAML, Okta, and Microsoft Entra)
  • 👮 RBAC with role mapping and team sync
  • 🗝️ Secrets management
• 🌎 Environments
  • 🔒 Per-environment network egress policies
  • 💸 Per-environment cost limits
• 🔭 Observability
  • 🪵 OpenTelemetry traces
  • 📊 Prometheus metrics
  • 📝 Logs
  • 💵 Per-team cost tracking

Already running dangerous single-tenant agents like Claude Cowork, OpenClaw, or Hermes in your enterprise? Migration Kit →

Quickstart

Run docker quickstart from https://archestra.ai/docs/platform-quickstart

👍 Ready for production

1. ✅ $13.5M total funding
2. ✅ Three Fortune-50 deployments
3. ✅ Lightning fast, 31ms at 95p: Performance & Latency benchmarks →
4. ✅ Terraform provider →
5. ✅ Helm Chart →

🤝 Contributing

We welcome contributions from the community!

• Contribution Guidelines →
• Developer Quickstart →
• Security & Bug Bounty →

Thank you for contributing and continuously making <b>Archestra</b> better, <b>you're awesome</b> 🫶

<a href="https://github.com/archestra-ai/archestra/graphs/contributors"> <img src="https://contrib.rocks/image?repo=archestra-ai/archestra" alt="Contributors" /> </a>

---

<div align="center"> <br /> <a href="https://www.archestra.ai/blog/archestra-joins-cncf-linux-foundation"><img src="docs/assets/linux-foundation-logo.webp" height="50" alt="Linux Foundation" /></a> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; <a href="https://www.archestra.ai/blog/archestra-joins-cncf-linux-foundation"><img src="docs/assets/cncf-logo.webp" height="50" alt="CNCF" /></a> </div>