archestra-ai/archestra
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
Implements non-probabilistic security controls including dual-LLM sub-agents and dynamic tool filtering to prevent prompt injection attacks and data exfiltration. Kubernetes-native orchestrator manages MCP server lifecycle, credentials, and OAuth while a private registry enables organization-wide tool governance. Provides comprehensive observability and cost optimization, with automatic model switching capable of reducing expenses up to 96%.
3,548 stars. Actively maintained with 344 commits in the last 30 days.
Stars
3,548
Forks
341
Language
TypeScript
License
AGPL-3.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
344
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/archestra-ai/archestra"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related servers
adriannoes/asap-protocol
Standard protocol for agent-to-agent communication with stateful orchestration, MCP-compatible...
agentralabs/agentic-time
Temporal reasoning for AI agents — deadlines, schedules, sequences, duration estimation (PERT),...
agentralabs/agentic-sdk
Shared contracts for the Agentra ecosystem — traits, types, and standards that all sisters implement
nookprotocol/nookplot
Decentralized coordination infrastructure for AI agents — identity, reputation, communication,...
xemantic/xemantic-ai-tool-schema-mdc
Adapting xemantic-ai-tool-schema to Model Context Protocol kotlin-sdk Tool input