Skip to content
Back to search

archestra

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/archestra-ai/archestra with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/archestra-ai/archestra'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/archestra-ai--archestra/badge.svg)](/listings/archestra-ai--archestra)

HTML

<a href="/listings/archestra-ai--archestra"><img src="/api/listings/archestra-ai--archestra/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

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://localhost:3000>. Full Docker / Helm / Kubernetes instructions live in the [quickstart docs](https://archestra.ai/docs/platform-quickstart).

Release channels

Archestra maintains two active release tracks: - **Stable releases** (e.g. `1.3.51`): Qualified, tested releases for production deployments. Archestra maintains one active stable release line at a time with security patches and bug fixes. - **Release candidates** (e.g. `1.4.0-rc.22`): Previews of upcoming features built directly from the `main` branch. They let you test new capabilities and provide feedback before they land in a stable release. The Docker tag `archestra/platform:latest` points to the newest release, so it usually runs a release candidate.

New features and bug fixes land on `main` first and ship in rolling beta releases. Fixes are then selectively backported to the supported stable branch. For production environments, pin an exact version tag or Helm chart version rather than tracking `latest`. See our [Release guide](platform/dev/RELEASE.md) for full release lifecycle details.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 137 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="logo.svg" alt="Archestra" width="520" />
  3. **Secure AI Platform**
  4. *Built on a strong security and observability foundation: SSO and RBAC,
  5. sandboxed code execution, Lethal-Trifecta guardrails,
  6. OpenTelemetry traces, and Prometheus metrics — first-class, not bolted on.*
  7. [![License](https://img.shields.io/badge/License-AGPL%203.0%20%2F%20Enterprise-blue.svg)](LICENSE.md)
  8. [![Release](https://img.shields.io/github/v/release/archestra-ai/archestra)](https://github.com/archestra-ai/archestra/releases)
  9. [![Contributors](https://img.shields.io/github/contributors/archestra-ai/archestra)](https://github.com/archestra-ai/archestra/graphs/contributors)
  10. [![Last commit](https://img.shields.io/github/last-commit/archestra-ai/archestra)](https://github.com/archestra-ai/archestra/commits/main)
  11. [![Commit activity](https://img.shields.io/github/commit-activity/m/archestra-ai/archestra)](https://github.com/archestra-ai/archestra/pulse)
  12. [Quickstart](https://archestra.ai/docs/get-started#run-archestra) &nbsp;·&nbsp;
  13. [Docs](https://archestra.ai/docs/get-started) &nbsp;·&nbsp;
  14. [Releases](https://github.com/archestra-ai/archestra/releases) &nbsp;·&nbsp;
  15. [Slack](https://archestra.ai/join-slack)
  16. <br />
  17. https://github.com/user-attachments/assets/912b85e2-ef14-4e83-a807-5e2a81457a88
  18. </div>
  19. ---
  20. ## What it does
  21. Point your users — or your agents, or Claude / Codex / Cursor — at one URL. Archestra handles the rest:
  22. - 💬 **Chat for non-technical users.** Internal AI assistant with
  23. [projects](https://archestra.ai/docs/chat/projects),
  24. [MCP apps](https://archestra.ai/docs/chat/apps), and
  25. [Slack](https://archestra.ai/docs/agents/triggers-and-channels/slack),
  26. [MS Teams](https://archestra.ai/docs/agents/triggers-and-channels/ms-teams), and
  27. [email](https://archestra.ai/docs/agents/triggers-and-channels/email)
  28. front-ends.
  29. - 🛠️ **Developer LLM & MCP portal.** One token for Claude Code, Codex,
  30. Cursor — see the [proxy](https://archestra.ai/docs/llm-proxy).
  31. - 🚪 **LLM gateway** for [any provider](https://archestra.ai/docs/llm-proxy/providers)
  32. (Anthropic, OpenAI, Azure, Bedrock, DeepSeek, …) with
  33. [cost limits](https://archestra.ai/docs/llm-proxy/costs-and-limits),
  34. [virtual API keys](https://archestra.ai/docs/llm-proxy/authentication),
  35. and [dynamic model routing](https://archestra.ai/docs/reference/clients/model-router-client-credentials).
  36. - 🔌 **MCP gateway** with [OAuth + On-Behalf-Of](https://archestra.ai/docs/mcp/authentication)
  37. so tools run as the user, not a shared service account.
  38. - 🤝 **A2A gateway** for [agent-to-agent triggers](https://archestra.ai/docs/agents/triggers-and-channels/webhook-a2a).
  39. - 📦 **Private MCP registry** so teams ship their own tools — see
  40. [registry docs](https://archestra.ai/docs/mcp/servers).
  41. - 🎼 **MCP orchestrator** with a
  42. [Kubernetes operator](https://archestra.ai/docs/mcp/servers#mcp-orchestrator) and
  43. [self-serve promotion](https://archestra.ai/docs/administration/environments).
  44. - 🤖 **Agent runtime** with [scheduled / email / webhook triggers](https://archestra.ai/docs/agents),
  45. [sub-agent delegation](https://archestra.ai/docs/agents),
  46. [reusable skills](https://archestra.ai/docs/agents/skills/sharing),
  47. sandboxed code execution, and a K8s-native filesystem.
  48. - 📚 **RAG knowledge base** plumbed via
  49. [connectors](https://archestra.ai/docs/knowledge/connectors) to
  50. your existing stack.
  51. - 🧩 **Mini app builder** — see [apps](https://archestra.ai/docs/chat/apps).
  52. - 🛡️ **Deterministic guardrails** for [tool calls](https://archestra.ai/docs/agents/guardrails) and
  53. [Lethal Trifecta](https://archestra.ai/docs/agents/guardrails#the-lethal-trifecta) protections.
  54. - 🪪 **Identity & access** with [SSO](https://archestra.ai/docs/administration/identity/sso)
  55. (OIDC, SAML, Okta, Entra), [RBAC with role mapping & team sync](https://archestra.ai/docs/administration/access-control),
  56. and [secrets management](https://archestra.ai/docs/administration/security/secrets-management).
  57. - 🌎 **Environments** with [per-env egress policies](https://archestra.ai/docs/administration/environments)
  58. and [per-env cost limits](https://archestra.ai/docs/llm-proxy/costs-and-limits).
  59. - 🔭 **Observability** out of the box: OpenTelemetry traces, Prometheus
  60. metrics, logs, [per-team cost tracking](https://archestra.ai/docs/llm-proxy/costs-and-limits).
  61. > Already running dangerous single-tenant agents like Claude Cowork,
  62. > OpenClaw, or Hermes in your enterprise? **[Migration Kit →](migration-kit/README.md)**
  63. ## Quickstart
  64. ```bash
  65. docker pull archestra/platform:latest
  66. docker run \
  67. -p 127.0.0.1:9000:9000 -p 127.0.0.1:3000:3000 \
  68. -e ARCHESTRA_QUICKSTART=true \
  69. -v /var/run/docker.sock:/var/run/docker.sock \
  70. -v archestra-postgres-data:/var/lib/postgresql/data \
  71. -v archestra-app-data:/app/data \
  72. archestra/platform:latest
  73. ```
  74. Open <http://localhost:3000>. Full Docker / Helm / Kubernetes instructions
  75. live in the [quickstart docs](https://archestra.ai/docs/get-started#run-archestra).
  76. ### Release channels
  77. Archestra maintains two active release tracks:
  78. - **Stable releases** (e.g. `1.3.51`): Qualified, tested releases for production deployments. Archestra maintains one active stable release line at a time with security patches and bug fixes.
  79. - **Release candidates** (e.g. `1.4.0-rc.22`): Previews of upcoming features built directly from the `main` branch. They let you test new capabilities and provide feedback before they land in a stable release. The Docker tag `archestra/platform:latest` points to the newest release, so it usually runs a release candidate.
  80. New features and bug fixes land on `main` first and ship in rolling beta releases. Fixes are then selectively backported to the supported stable branch. For production environments, pin an exact version tag or Helm chart version rather than tracking `latest`. See our [Release guide](platform/dev/RELEASE.md) for full release lifecycle details.
  81. ## Ready for production
  82. - ✅ $13.5M total funding
  83. - ✅ Three Fortune-50 deployments
  84. - ✅ 31 ms at p95 — [performance benchmarks →](https://archestra.ai/docs/administration/observability/performance-benchmarks)
  85. - ✅ [Terraform provider →](https://github.com/archestra-ai/terraform-provider-archestra)
  86. - ✅ [Helm chart →](https://archestra.ai/docs/administration/deployment#helm-deployment-recommended-for-production)
  87. ## Deeper docs
  88. - 📖 [**Platform overview**](https://archestra.ai/docs/get-started) —
  89. what's in the box, how the pieces fit together.
  90. - 📐 [**Deployment**](https://archestra.ai/docs/administration/deployment) —
  91. Docker, Helm, Kubernetes, every env var, secrets management.
  92. - 💰 [**Pricing model**](https://archestra.ai/docs/get-started/pricing) —
  93. Open Core, free for teams under 30 users, enterprise licensing.
  94. - 🛡️ [**Security & bug bounty**](https://archestra.ai/docs/contributing/security)
  95. - 🤝 [**Contributing**](https://archestra.ai/docs/contributing) —
  96. set up the dev env, run e2e tests, open a PR.
  97. - [**Release guide**](platform/dev/RELEASE.md) —
  98. beta releases, stable patches, cutovers, and qualification.
  99. Thank you for continuously making **Archestra** better — you're awesome 🫶
  100. <a href="https://github.com/archestra-ai/archestra/graphs/contributors">
  101. <img src="https://contrib.rocks/image?repo=archestra-ai/archestra" alt="Contributors" />
  102. </a>
  103. ---
  104. <div align="center">
  105. <br />
  106. <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>
  107. &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
  108. <a href="https://www.archestra.ai/blog/archestra-joins-cncf-linux-foundation"><img src="docs/assets/cncf-logo.webp" height="50" alt="CNCF" /></a>
  109. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.