Open source. Open possibilities.

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.

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.

Self-hosted AI API gateway that gathers upstream LLM provider keys as channels, exposes unified OpenAI and Anthropic endpoints with automatic protocol conversion, and tracks token usage, cache hit rate and per-key statistics in real time. Go + React, shipped as one binary.

SafeLine is a self-hosted web application firewall and reverse proxy that sits in front of web apps to filter and block malicious HTTP/S traffic, offering rate limiting, bot and authentication challenges, dynamic HTML/JS encryption and access control lists.

Provider-neutral FastAPI gateway for LLM routing, retries, fallbacks, structured output, and usage/cost accounting. Supports Gemini and OpenAI with model aliases, retry policies, and persistent usage tracking.

Token Station is a local routing gateway for AI agents and LLM providers. Route Claude Code, Cursor, Codex, Gemini CLI and others through a loopback-only gateway with smart tier selection, quota-aware routing, and usage tracking.

Stateless LLM API gateway routing OpenAI, Anthropic, and Gemini requests across multiple providers with cross-dialect translation, usage metering, and single-binary deployment.

A dependency-free Python library that translates various LLM APIs into OpenAI-compatible format and enables automatic failover between providers.

Higress is a cloud-native AI-native API gateway built on Istio and Envoy, featuring Wasm plugin extensibility, unified LLM provider access, MCP server hosting, and Kubernetes ingress support.

One API is a unified LLM API management and distribution system supporting dozens of mainstream models including OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, and more. It provides a unified OpenAI-compatible interface, token management, channel load balancing, user grouping, and redistribution features, deployable via single binary or Docker in one click.

A high-availability proxy for Claude Code that routes requests across five Chinese AI providers with automatic failover, circuit breaking, and zero-downtime configuration.

Kong Gateway is a cloud-native, platform-agnostic API, LLM and MCP gateway with plugin-based extensibility, routing, load balancing, authentication and AI traffic features.

A fully serverless, event-driven clickstream data pipeline on AWS that ingests, transforms, and stores clickstream events in Parquet format using API Gateway, Kinesis, Firehose, Lambda, and Athena, with production-ready IaC via AWS SAM.

Apache APISIX is a dynamic, real-time, high-performance cloud-native API and AI gateway built on NGINX and etcd, offering dynamic routing, plugin hot-loading, multi-protocol support, and AI proxying for LLM workloads.

Unified API gateway for local and remote LLMs, exposing OpenAI-compatible endpoint to route requests across providers like OpenAI, Anthropic, Gemini, and Ollama.

A lightweight OpenAI/Anthropic relay gateway with credential pooling, failover, and automated New API channel synchronization using only SQLite.