# archestra-ai/archestra

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

Repository: https://github.com/archestra-ai/archestra
Canonical: https://ross.abutalabs.com/products/archestra
Homepage: https://Archestra.AI
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: a2a, acp, agent, ai, mcp, mcp-client, mcp-server, runtime, mcp-host, mcp-servers, mcp-tools, claude, deepseek, gemini, openai, a2a-mcp, chatgpt, chatgpt-api, k8s, mcp-gateway
Last push: 2026-08-26T22:57:27+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 29
- inputs: {"age_days": 414, "days_push": 7, "days_rel": 8, "gap_med": 0, "n_releases_24m": 268}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4232, forks 1182 (observed 2026-08-28T04:08:39.460481+00:00)

## What it is
Archestra is an open-source, self-hosted enterprise AI platform combining an agentic chat UI, agent runtime, LLM gateway/proxy, MCP gateway, private MCP registry, and Kubernetes-based MCP orchestrator. It ships with enterprise features like SSO/RBAC, prompt-injection-resistant guardrails, sandboxed code execution, OpenTelemetry tracing, and per-team cost tracking.

## Use cases
- self-host an internal ChatGPT-like assistant for my company
- run MCP servers securely in Kubernetes with per-user identity
- put a gateway in front of OpenAI, Anthropic, and other LLM providers with cost limits
- give non-technical teams an AI chat with SSO and RBAC
- host a private MCP registry for my team's tools
- add guardrails against prompt injection to agent tool calls
- proxy Claude Code or Cursor through one enterprise endpoint
- build and schedule autonomous agents with MCP tools and triggers

## When to choose
- you need a centralized, self-hosted AI platform serving both engineers and non-technical staff
- you want MCP gateway, registry, and orchestration with OAuth on-behalf-of semantics
- enterprise requirements like SSO, RBAC, audit logs, observability, and cost tracking are mandatory
- you want drop-in LLM/MCP proxies that work with LangChain, n8n, Vercel AI, or Pydantic AI

## When to avoid
- you only need a lightweight LLM API client or SDK in application code
- you want a fully permissive-licensed project (it is AGPL 3.0 with enterprise licensing)
- you need a minimal single-purpose tool rather than a full multi-component platform
- you cannot run Kubernetes or containerized infrastructure for the orchestrator

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, mcp, rag, chatbot, chat-interface, api-gateway, auth, authorization, monitoring, tracing, security, self-hosted, workflow-automation, scheduling, webhook
- domain: artificial-intelligence, large-language-models, chatbots, self-hosted, developer-tools, security
- platform: self-hosted, cloud
- tags: mcp-gateway, mcp-registry, mcp-orchestrator, llm-gateway, llm-proxy, a2a, agent-platform, enterprise-ai, guardrails, sso, rbac, opentelemetry, prometheus, kubernetes-operator, agentic-chat, agent-skills, cost-tracking, ai-agents, retrieval-augmented-generation, devops, docker, kubernetes, web-server, typescript

## Member repositories
- archestra-ai/archestra (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:39.460481+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:20.133751+00:00, confidence not recorded.
  - readme: https://github.com/archestra-ai/archestra (fetched 2026-08-28T04:08:39.460481+00:00, sha 3b5110fdb638)
  - homepage: https://Archestra.AI (fetched 2026-08-29T09:12:46.428302+00:00, sha 8d9328f5c620)
  - site_page: https://archestra.ai/docs (fetched 2026-08-29T09:12:46.438002+00:00, sha 9126aa02e787)
  - site_page: https://archestra.ai/about (fetched 2026-08-29T09:12:46.439950+00:00, sha e431efdc87b4)
  - site_page: https://archestra.ai/docs/platform-chat (fetched 2026-08-29T09:12:46.441774+00:00, sha 7a4dc364638a)
  - site_page: https://archestra.ai/docs/platform-sso (fetched 2026-08-29T09:12:46.443610+00:00, sha f5154e95e597)
  - site_page: https://archestra.ai/docs/platform-agent-skills (fetched 2026-08-29T09:12:46.445367+00:00, sha ca737118efa0)
  - site_page: https://archestra.ai/docs/platform-apps (fetched 2026-08-29T09:12:46.447555+00:00, sha ef47899feebd)
  - site_page: https://archestra.ai/docs/platform-projects (fetched 2026-08-29T09:12:46.450380+00:00, sha f5c039a82b51)
  - site_page: https://archestra.ai/docs/platform-access-control (fetched 2026-08-29T09:12:46.452625+00:00, sha d9d9a0206655)
- Data as of 2026-08-30T08:39:29.467469+00:00.