archestra
View on GitHubEnterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
An enterprise AI platform combining an MCP gateway and private registry with an LLM gateway, agent runtime, orchestration, guardrails, and observability. Supports Kubernetes deployments and integrations with common LLM providers and developer clients.
Use Cases
Route MCP clients through a centrally managed gatewayRegister and distribute private MCP toolsManage OAuth and user-delegated access for MCP toolsProxy requests to multiple LLM providersApply model routing and cost limitsRun scheduled, email, and webhook-triggered agentsOrchestrate agents and delegate to sub-agentsConnect enterprise data sources to a RAG knowledge baseMonitor AI usage with traces, metrics, and cost tracking
Built With
- Language
- TypeScript
- Frameworks
- Kubernetes · OpenTelemetry · Prometheus
Tags
MCP gateway · MCP registry · LLM gateway · AI agents · agent orchestration · A2A · guardrails · RAG · OAuth · RBAC · observability · Kubernetes