archestra
starsforks
How to install archestra?
archestra-ai/archestra
$git clone https://github.com/archestra-ai/archestraThe all-in-one open-source enterprise AI platform.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | <img src="logo.svg" alt="Archestra" width="520" /> |
| 4 | |
| 5 | **The all-in-one open-source enterprise AI platform.** |
| 6 | |
| 7 | *Built on a strong security and observability foundation: SSO and RBAC, |
| 8 | sandboxed code execution, Dual-LLM and Lethal-Trifecta guardrails, |
| 9 | OpenTelemetry traces, and Prometheus metrics — first-class, not bolted on.* |
| 10 | |
| 11 | [](LICENSE.md) |
| 12 | [](https://github.com/archestra-ai/archestra/releases) |
| 13 | [](https://github.com/archestra-ai/archestra/graphs/contributors) |
| 14 | [](https://github.com/archestra-ai/archestra/commits/main) |
| 15 | [](https://github.com/archestra-ai/archestra/pulse) |
| 16 | |
| 17 | [Quickstart](https://archestra.ai/docs/platform-quickstart) · |
| 18 | [Docs](https://archestra.ai/docs/platform-overview) · |
| 19 | [Releases](https://github.com/archestra-ai/archestra/releases) · |
| 20 | [Slack](https://archestra.ai/join-slack) |
| 21 | |
| 22 | <br /> |
| 23 | |
| 24 | <video src="https://github.com/user-attachments/assets/4b278679-9615-4d4a-9bd0-57d0585041c4" controls playsinline width="800"></video> |
| 25 | |
| 26 | </div> |
| 27 | |
| 28 | --- |
| 29 | |
| 30 | ## What it does |
| 31 | |
| 32 | Point your users — or your agents, or Claude / Codex / Cursor — at one URL. Archestra handles the rest: |
| 33 | |
| 34 | - 💬 **Chat for non-technical users.** Internal AI assistant with |
| 35 | [projects](https://archestra.ai/docs/platform-projects), |
| 36 | [MCP apps](https://archestra.ai/docs/platform-apps), and |
| 37 | [Slack](https://archestra.ai/docs/platform-slack), |
| 38 | [MS Teams](https://archestra.ai/docs/platform-ms-teams), and |
| 39 | [email](https://archestra.ai/docs/platform-agent-triggers-email) |
| 40 | front-ends. |
| 41 | - 🛠️ **Developer LLM & MCP portal.** One token for Claude Code, Codex, |
| 42 | Cursor — see the [proxy](https://archestra.ai/docs/platform-llm-proxy). |
| 43 | - 🚪 **LLM gateway** for [any provider](https://archestra.ai/docs/platform-supported-llm-providers) |
| 44 | (Anthropic, OpenAI, Azure, Bedrock, DeepSeek, …) with |
| 45 | [cost limits](https://archestra.ai/docs/platform-costs-and-limits), |
| 46 | [virtual API keys](https://archestra.ai/docs/platform-llm-proxy-authentication), |
| 47 | and [dynamic model routing](https://archestra.ai/docs/platform-model-router-client-credentials-example). |
| 48 | - 🔌 **MCP gateway** with [OAuth + On-Behalf-Of](https://archestra.ai/docs/mcp-authentication) |
| 49 | so tools run as the user, not a shared service account. |
| 50 | - 🤝 **A2A gateway** for [agent-to-agent triggers](https://archestra.ai/docs/platform-agent-triggers-webhook-a2a). |
| 51 | - 📦 **Private MCP registry** so teams ship their own tools — see |
| 52 | [registry docs](https://archestra.ai/docs/platform-private-registry). |
| 53 | - 🎼 **MCP orchestrator** with a |
| 54 | [Kubernetes operator](https://archestra.ai/docs/platform-orchestrator) and |
| 55 | [self-serve promotion](https://archestra.ai/docs/platform-environments). |
| 56 | - 🤖 **Agent runtime** with [scheduled / email / webhook triggers](https://archestra.ai/docs/platform-agents), |
| 57 | [sub-agent delegation](https://archestra.ai/docs/platform-agents), |
| 58 | [reusable skills](https://archestra.ai/docs/platform-agent-skills-sharing), |
| 59 | sandboxed code execution, and a K8s-native filesystem. |
| 60 | - 📚 **RAG knowledge base** plumbed via |
| 61 | [connectors](https://archestra.ai/docs/platform-knowledge-connectors) to |
| 62 | your existing stack. |
| 63 | - 🧩 **Mini app builder** — see [apps](https://archestra.ai/docs/platform-apps). |
| 64 | - 🛡️ **Deterministic guardrails** for [tool calls](https://archestra.ai/docs/platform-ai-tool-guardrails), |
| 65 | [Dual-LLM](https://archestra.ai/docs/platform-built-in-subagents#dual-llm-agent) verification, and |
| 66 | [Lethal Trifecta](https://archestra.ai/docs/platform-ai-tool-guardrails#the-lethal-trifecta) protections. |
| 67 | - 🪪 **Identity & access** with [SSO](https://archestra.ai/docs/platfo |
People who liked this also viewed
6 picksType
- mcp-proxy-for-awsAWS MCP Proxy ServerMCP ServersJul 2026
- pydantic-ai-backendFile Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.MCP ServersJul 2026
- mcp-for-argocdAn implementation of Model Context Protocol (MCP) server for Argo CD.MCP ServersJul 2026
- heroku-mcp-serverHeroku Platform MCP Server using the Heroku CLIMCP ServersJul 2026
- ghost-mcpA Model Context Protocol (MCP) server for interacting with Ghost CMS through LLM interfaces like Claude. Allow you to control your Ghost blog by simply asking Claude etc.MCP ServersApr 2026
- Google DriveUpload, organize, and share files in the cloud. Manage folders, set permissions, and search across stored documents.MCP Serversrecently
