archestra
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
What is archestra?
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
Overview of archestra
What it is
Archestra is an enterprise AI platform that provides a unified interface for users, agents, and developer tools. It includes guardrails, an MCP (Model Context Protocol) registry, a gateway, and an orchestrator. The platform is built on a foundation of security and observability, with features such as SSO, RBAC, sandboxed code execution, OpenTelemetry traces, and Prometheus metrics.
Key features
- Chat interface for non-technical users with integrations for Slack, MS Teams, and email.
- Developer LLM and MCP portal with a single token for Claude Code, Codex, and Cursor.
- LLM gateway supporting multiple providers (Anthropic, OpenAI, Azure, Bedrock, DeepSeek) with cost limits, virtual API keys, and dynamic model routing.
- MCP gateway with OAuth and On-Behalf-Of authentication.
- Private MCP registry for teams to ship their own tools.
- MCP orchestrator with a Kubernetes operator and self-serve promotion.
- Agent runtime with scheduled, email, and webhook triggers, sub-agent delegation, reusable skills, sandboxed code execution, and a K8s-native filesystem.
- RAG knowledge base with connectors to existing stacks.
- Deterministic guardrails for tool calls and Lethal Trifecta protections.
- Identity and access management with SSO (OIDC, SAML, Okta, Entra), RBAC, role mapping, team sync, and secrets management.
- Environments with per-env egress policies and cost limits.
- Observability with OpenTelemetry traces, Prometheus metrics, logs, and per-team cost tracking.
Use cases
Archestra is designed for enterprises that need a secure, observable AI platform. It can be used to provide an internal AI assistant for non-technical staff, a developer portal for LLM and MCP tools, and a gateway for managing multiple AI providers. It also supports agent-to-agent communication, private tool registries, and sandboxed code execution for safe automation.
Getting started
bash docker pull archestra/platform:latest docker run -p 127.0.0.1:9000:9000 -p 127.0.0.1:3000:3000 -e ARCHESTRA_QUICKSTART=true -v /var/run/docker.sock:/var/run/docker.sock -v archestra-postgres-data:/var/lib/postgresql/data -v archestra-app-data:/app/data archestra/platform:latest Open http://127.0.0.1:3000. Full Docker, Helm, and Kubernetes instructions are in the quickstart docs.
License and pricing
The license is not stated in the provided metadata. The README mentions an Open Core model, free for teams under 30 users, and enterprise licensing. For exact terms, see the repository README.
Based on the project's public README and repository metadata.