Freellmpool
OpenAI-compatible MCP gateway pooling 24 LLM providers with routing, failover, quota, and tools.
- Transport
- Not stated
- Package
- —
- Registry id
- io.github.0xzr/freellmpool
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
freellmpool is a free, open-source, MIT-licensed gateway that exposes one OpenAI-compatible endpoint backed by cataloged routes across 22 providers. It runs as a command-line tool, a Python library, a local proxy, and an MCP server. Several providers need no API key, so a fresh install can answer without signup when a keyless provider is up.
It includes automatic failover when a provider is rate-limited and per-day quota tracking across tiers. The proxy speaks the OpenAI API and includes an experimental Anthropic-compatible path, so existing apps and coding agents can run on pooled free models. It is MIT-licensed and free to use.
freellmpool can discover and use local models from LM Studio, Ollama, and llama.cpp.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.