Logo
Deploy Now

Categories

Developer Tools DevOps MCP API Gateway AI Platform Agent Orchestration Enterprise AI LLM Gateway

Developer links

Last Updated: 01-01-2023 12:00 AM (UTC)

Archestra

Archestra delivers the enterprise AI infrastructure layer that organizations need when managing multiple LLM providers, MCP servers, and AI agents across teams becomes unmanageable. The LLM gateway routes requests across Anthropic, OpenAI, Azure, Bedrock, and DeepSeek with virtual API keys, per-team cost limits, and dynamic model routing — giving every developer one token for Claude Code, Cursor, or Codex while finance tracks spend per department. The MCP gateway authenticates tool calls with OAuth 2.1 and On-Behalf-Of tokens so each tool executes as the calling user, not a shared service account, eliminating credential sprawl. The private MCP registry lets teams publish custom tool servers with approval flows promoting servers from dev through staging to production, each environment maintaining its own credentials and network egress policies. The Kubernetes operator manages MCP server lifecycle — deploying containers, scaling, health-checking, and routing gateway traffic to local servers automatically. The agent runtime supports scheduled triggers, email and webhook invocations, sub-agent delegation, reusable skills, and sandboxed code execution with a K8s-native filesystem. Deterministic guardrails including Dual-LLM verification and Lethal Trifecta protections prevent dangerous tool calls before execution. Built-in OpenTelemetry traces and Prometheus metrics provide full observability without additional tooling. Docker deployment exposes the Admin UI on port 3000 and API on port 9000 with a single command. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Archestra
Archestra
Archestra
Archestra
Archestra

Benefits

  • One Gateway All Providers
  • Route LLM requests across Anthropic, OpenAI, Azure, Bedrock, and DeepSeek with virtual API keys, per-team cost limits, and dynamic model routing from a single endpoint.
  • OAuth Tool Authentication
  • MCP gateway uses OAuth 2.1 and On-Behalf-Of tokens so every tool call executes as the calling user, eliminating shared service accounts and credential sprawl across teams.
  • Deterministic Guardrails Built In
  • Dual-LLM verification and Lethal Trifecta protections block dangerous tool calls before execution. No probabilistic filters — deterministic rules enforce tool call safety policies.
  • Full Observability No Setup
  • OpenTelemetry traces, Prometheus metrics, per-team cost tracking, and audit logs ship ready without configuring external collectors or dashboards on initial deployment.

Features

  • Private MCP Registry
  • Teams publish custom MCP tool servers with approval workflows promoting servers through dev, staging, and production environments with isolated credentials.
  • Kubernetes MCP Orchestrator
  • Operator deploys MCP servers as containers, manages lifecycle, scales instances, health-checks endpoints, and routes gateway traffic automatically within the cluster.
  • Agent Runtime Engine
  • Schedule agents via cron, email, or webhook triggers with sub-agent delegation, reusable skills, sandboxed code execution, and K8s-native filesystem access.
  • LLM Cost Management
  • Virtual API keys with per-team and per-environment cost limits, usage dashboards, and automatic enforcement prevent budget overruns across departments.
  • Docker Single-Command Deploy
  • One Docker run command provisions Admin UI on port 3000, API on port 9000, PostgreSQL data persistence, and optional KinD for MCP orchestration.