mcp-gateway

BerriAI/litellm

LiteLLM moves to a Rust core for a leaner AI gateway — LiteLLM now ships a Rust core under its Python SDK, aiming to be a faster, lighter self-hosted AI gateway. It unifies 100+ LLM APIs (Bedrock, Azure, OpenAI, Anthropic, VertexAI, vLLM, Nvidia NIM) in OpenAI format, adding cost tracking, guardrails, load balancing and logging for teams running LLMOps at scale.

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

Kong/kong

🦍 The API and AI Gateway

casdoor/casdoor

Casdoor extends its IAM stack to cover MCP and AI agent auth — Casdoor is a self-hosted SSO/IAM server supporting OAuth2, OIDC, SAML, LDAP, SCIM, WebAuthn and MFA. It now also adds MCP gateway support and agent-first auth flows for tools like OpenClaw, making it relevant for teams securing LLM agents alongside traditional enterprise identity providers like Google Workspace and Azure AD.

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

Nasiko-Labs/nasiko

Tracking what coding agents actually cost, across every harness — Nasiko discovers running coding agents like Claude Code, Codex, Cursor or OpenCode, unifies their spend into one schema, and lets teams route them to chosen models without changing existing harness workflows. Built for developers and teams who need vendor-neutral cost visibility and control over AI agent spend.

The Open Runtime for AI Agents

maximhq/bifrost

A zero-config gateway unifying 23+ LLM providers behind one API — Bifrost is a Go-based AI gateway giving one OpenAI-compatible API across 23+ providers, with automatic failover, load balancing, semantic caching, virtual keys and budgets. It deploys in seconds via npx or Docker, includes a web UI for config and monitoring, and adds under 200µs overhead at 5k RPS—aimed at teams building reliable, multi-provider AI apps and agents.

Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

agentgateway/agentgateway

A dedicated proxy layer for MCP and A2A agent traffic — agentgateway is a Rust-based proxy built specifically for AI-native protocols like MCP and A2A, aiming to be a complete connectivity layer for agentic AI systems. It targets teams running AI agents and MCP servers who need gateway, routing, and service-mesh capabilities, including Kubernetes-native deployments via Gateway API.

Next Generation Agentic Proxy for AI Agents and MCP servers

dagucloud/dagu

A single-binary DAG engine for teams that just need jobs to run — Dagu turns existing scripts, SSH commands, and containers into scheduled workflows without a database or message broker. It's a self-hostable single binary with a Web UI, built for ops and automation teams rather than data-pipeline specialists, and now includes an MCP server for AI-agent integration.

Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.

HelpCode-ai/anythingmcp

Self-hosted gateway that wraps 517 APIs as MCP tools — AnythingMCP connects REST/OpenAPI, SOAP, GraphQL, OData and SQL systems to Claude, ChatGPT and Copilot without writing a custom MCP server. It ships 517 ready-made connectors, including SAP, Etsy and Amazon Seller, with 23 needing no API key, plus RBAC, SSO and audit logs for enterprise use.

MCP gateway for AI agents: turn any REST/OpenAPI, GraphQL, SOAP or SQL API into MCP tools. 562 ready-made connectors (SAP, ERP, e-commerce) with RBAC, SSO, audit logs and a knowledge graph.

openai/tunnel-client

OpenAI's own client for tunneling private MCP servers to ChatGPT — A Go CLI and SDK from OpenAI that lets private or localhost MCP servers reach ChatGPT, Codex, the Responses API, and AgentKit via a hosted tunnel endpoint, with no inbound firewall rules needed. Useful for teams blocked by security policy from exposing MCP servers publicly, with built-in healthz/readyz/metrics/ui for operators.

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

antropos17/Aegis

Local, Windows-first security dashboard for watching AI agents — AEGIS is an Electron/Svelte desktop app that monitors AI coding agents like Claude Code on your own machine: process trees, file and network activity, token usage, and anomaly scoring against rolling session baselines. It adds opt-in action policies and MCP gateways plus experimental Hyper-V guest execution, aimed at developers who want local-first oversight of agentic tools rather than a cloud service.

Windows-first desktop oversight for AI agents: live monitoring, local security reviews, token usage, audit reports and opt-in action policies/MCP gateways. Experimental Hyper-V guest execution; macOS/Linux experimental.