TheLunarCompany/lunar

lunar.dev: Agent native MCP Gateway for governance and security

What it solves

Lunar.dev provides a mediation layer for applications and AI agents that rely on external APIs. It solves the problem of fragmented API consumption, providing a central point to manage, govern, and optimize how agents and apps call third-party services, preventing issues like cost overruns, unmonitored token usage, and unreliable service dependencies.

How it works

It acts as a unified API Gateway for AI. The platform consists of two main components: the Lunar Proxy, which serves as the core control layer for traffic shaping and policy enforcement, and Lunar MCPX, a zero-code aggregator that consolidates multiple Model Context Protocol (MCP) servers into a single gateway for easier management.

Who it’s for

It is designed for developers and organizations building AI agents and autonomous workflows that need production-ready API management, observability, and governance at scale.

Highlights

  • Live Traffic Visibility: Real-time metrics on latency, errors, cost, and token usage for LLM and agent calls.
  • AI-Aware Policy Enforcement: Fine-grained rules to control tool access and throttle agentic traffic.
  • Traffic Shaping: Tools for rate limiting, retries, priority queues, and circuit breakers.
  • MCP Aggregation: Centralized consolidation of multiple MCP servers into one gateway.
  • Cost Optimization: Identification of waste and smoothing of traffic peaks to reduce API costs.

Related

  • Project
    theopenco/llmgateway

    LLM Gateway is an open‑source API gateway that provides a single OpenAI‑compatible endpoint for routing requests to multiple LLM providers, centralising API‑key management and offering built‑in usage and performance analytics. It can be used as a hosted SaaS service or self‑hosted via Docker.

  • Project
    obot-platform/obot

    An open-source platform for organizations to manage, secure, and govern their AI ecosystems, providing centralized control over LLM access, MCP servers, and AI activity auditing.

  • Project
    agentgateway/agentgateway

    An open-source proxy that provides security, observability, and governance for agent-to-LLM, agent-to-tool, and agent-to-agent communication.

  • Project
    fruitbars/simple-one-api

    simple‑one‑api is an open‑source Go gateway that unifies multiple LLM providers behind OpenAI‑compatible endpoints, adds capacity‑aware key scheduling, four‑layer rate‑limiting, a built‑in React chat UI, a visual config console, and a Wails desktop client. It can be run as a single binary, Docker container, or desktop app, and stores its configuration in SQLite.

  • Project
    bestruirui/octopus

    An LLM API aggregation service that unifies multiple AI providers into a single interface with protocol conversion and automatic failover.