Self-hosted OpenAI-compatible gateway that load-balances multiple model upstreams
- Open source
- 3 Hacker News points
- Developer tools

Self-hosted OpenAI-compatible gateway that load-balances multiple model upstreams

Self-hosted AI gateway routing many providers through one local endpoint with fallback

Open-source AI gateway in Go that routes LLM calls with budgets, fallbacks and MCP
Rust gateway that proxies OpenAI and Anthropic APIs and records each generation
OpenAI-compatible gateway to around 1,000 LLMs with routing, cost tracking and team
Self-hosted proxy that logs token use, cost and latency for LLM API calls and enforces key

Ruby library with one API for 23 AI providers, tools and Rails conventions

Desktop app to switch API providers and manage MCP, Skills and prompts across AI coding

Open-source gateway adding identity, policy and audit between AI agents and your systems
Lightweight async Python client for multiple LLM providers with agent and MCP support
Local reverse proxy that redacts names and secrets before prompts reach LLM APIs
Open OpenAI-compatible LLM inference engine for AWS Trainium2 with NKI megakernels
The closest alternatives to gateway are ShanHaiGateway, OmniRoute, bifrost, langfuse and Eden AI.
Yes. ShanHaiGateway, OmniRoute, bifrost have a free or open-source option.