LiteLLMAIOpen
Open-source AI gateway unifying 100+ LLMs behind one API
LiteLLM is an open-source AI gateway that calls more than 100 large language model providers through one OpenAI-compatible interface.
Tag
8 catalogue entries use this topic; each Project's license policy is labeled separately.
Open-source AI gateway unifying 100+ LLMs behind one API
LiteLLM is an open-source AI gateway that calls more than 100 large language model providers through one OpenAI-compatible interface.
Self-hosted OpenAI-compatible runtime for local AI models
LocalAI is a self-hosted runtime that runs AI models locally behind OpenAI-compatible endpoints.
Open-source desktop app for chatting with AI models fully offline
Jan is a free, open-source desktop app for chatting with AI models on your own computer, working fully offline once models are downloaded.
Open-source AI gateway routing 200+ providers with fallbacks
Portkey AI Gateway is an open-source gateway that routes app traffic across 200+ LLM providers with fallbacks, load balancing, caching, and guardrails.
Self-hosted LLM gateway with one OpenAI-compatible API
Bifrost is a self-hosted gateway that puts every large language model call behind one OpenAI-compatible API. An application points its existing OpenAI client at the gateway, and Bifrost routes the request to whichever provider is configured, so switching models or spreading load across providers is a configuration change rather than a rewrite.
Self-hosted AI gateway routing LLM traffic through Envoy
Envoy AI Gateway is a self-hosted gateway that routes application traffic to 17 language model providers through one OpenAI-compatible API.
Open-source proxy securing AI API keys in iOS apps with DeviceCheck
Proxed AI is an open-source proxy that keeps AI API keys off iOS devices, checking each request with Apple DeviceCheck while adding rate limits and usage tracking.
Open-source, OpenAI-compatible LLM gateway with cost and latency tracking
LLM Gateway is an open-source gateway that puts OpenAI, Anthropic, and Gemini calls behind one OpenAI-compatible API. An application keeps its existing OpenAI client and points it at the gateway, so switching providers or spreading load across them is a configuration change rather than a rewrite.