Open source. Open possibilities.

Jano is a lightweight OpenAI-compatible router that enables multiple local LLMs to share one GPU by intelligently batching requests and minimizing model swaps.

A high-performance Rust gateway that unifies APIs for multiple LLM providers with automatic load balancing and rate limiting.

Zuzia Relay is a CLI-first AI gateway for Node.js that provides a single OpenAI-compatible endpoint for multiple AI providers.

An MCP server that integrates the Godot game engine into AI assistants, enabling scene authoring, type-checked scripting, and live debugging.

AI Gateway routes LLM requests intelligently by intent, cost, and provider health. Supports multi-tenant access, caching, failover, and observability — reducing costs and improving reliability for production AI apps.

A self-hosted reverse proxy for LLM APIs that provides transparent request forwarding with integrated recording, caching, rate-limiting, and analytics.

Restage is a server-driven UI toolkit for Flutter that allows developers to ship UI updates over the air using their own widgets and themes.

Enterprise-grade LLM gateway built with Java 21 and Spring Boot, supporting multi-tenant access, model routing, audit, cost tracking, and OpenAI/Anthropic API compatibility.

Clousight Bench is an evaluation tool for cloud computing that measures cloud products and services using unmodified, recognized benchmark suites across multiple product categories.

Python and MCP example for an Apify actor that returns US House and Senate congressional stock trades and financial disclosures as structured JSON, with filters for member, ticker, and date range.

llm-apipool aggregates 40+ free LLM APIs into one OpenAI-compatible endpoint. Auto-rotates keys, handles rate limits, tracks usage, and supports CLI, TUI, proxy, and LangChain integration.

A lightweight OpenAI API reverse proxy featuring per-key token budgets, rate limiting, cost dashboards, and automatic model downgrading.

Minimal FastAPI proxy for OpenAI Chat Completions and Embeddings APIs. Supports multi-tenant key mapping, streaming, and official SDK compatibility without a database.

A Go SDK for building Model Context Protocol (MCP) servers, enabling LLM applications to securely integrate with external data sources, tools, and prompts through a standardized protocol.

OpenAI-compatible proxy for Gemini Web API using cookie-based auth. Supports streaming, tool calling, and multiple models without API keys.

nexus-vscode is an MCP proxy extension for VSCode and Cursor that forwards AI tool calls to Unreal Engine (UE) instances.

CCProxy is a local, plugin-based reverse proxy that provides unified API access to multiple AI providers including Claude, OpenAI Codex, and GitHub Copilot.

Nexus Orchestrator is a self-hosted orchestration layer that intelligently routes LLM requests to the most suitable local or cloud models based on prompt intent.

CogniGate is a self-hosted, multi-tenant LLM gateway that provides a single OpenAI-compatible endpoint to manage multiple model providers while keeping credentials secure.

OmniRoute is an open-source MIT-licensed AI gateway providing one unified endpoint to access 352+ AI providers and 1200+ models (150+ free tiers). It features quota-aware auto-fallback, token compression saving 15–95%, and integrates with Claude Code, Cursor, Cline, and other coding agents.