Archestra brings chat, agent runtime, MCP registry, MCP gateway, A2A triggers, and guardrails into one platform. It also adds SSO, RBAC, secrets, observability, and environment controls so teams can run agents in production.
Builders who want one secured place to run and govern agents, tools, and AI apps.
You can put agents and AI tools behind one platform instead of stitching together separate services.
Routes MCP tools through a gateway and lets teams publish private tools in a registry.
Runs agents with scheduled, email, and webhook triggers, sub-agent delegation, reusable skills, and sandboxed code execution.
Provides one access layer for providers like Anthropic, OpenAI, Azure, Bedrock, and DeepSeek, with routing and cost limits.
Adds deterministic tool-call guardrails, Dual-LLM verification, and Lethal Trifecta protections.
Supports SSO, RBAC, team sync, role mapping, and secrets management.
Includes OpenTelemetry traces, Prometheus metrics, logs, per-team cost tracking, and per-environment policies.
The all-in-one open-source enterprise AI platform.
Built on a strong security and observability foundation: SSO and RBAC, sandboxed code execution, Dual-LLM and Lethal-Trifecta guardrails, OpenTelemetry traces, and Prometheus metrics — first-class, not bolted on.
Quickstart · Docs · Releases · Slack
Point your users — or your agents, or Claude / Codex / Cursor — at one URL. Archestra handles the rest:
Already running dangerous single-tenant agents like Claude Cowork, OpenClaw, or Hermes in your enterprise? Migration Kit →
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.
Archestra maintains two active release tracks:
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. The Docker tag latest points to the most recent stable release.1.4.0-beta.1): Previews of upcoming features built directly from the main branch. Beta releases let you test new capabilities and provide feedback before they land in a stable release.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 for full release lifecycle details.
Thank you for continuously making Archestra better — you're awesome 🫶
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.
OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research.
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
😎 Awesome lists about all kinds of interesting topics [NOTE: Pull requests are temporarily disabled until I have a chance to catch up with the existing ones]
AIPOCH Open-Science is an open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, with scientific agents, Python/R notebooks, data connectors, and reproducible provenance.