hadihonarvar/flock
Self-hosted LLM gateway. One Go binary turns your Macs and Linux boxes into a private inference cluster — multi-machine routing, sharding via llama.cpp-RPC, per-user keys + quotas + audit, OpenAI- and Anthropic-compatible APIs behind one endpoint. Point Cursor / Claude Code / Aider / SDKs at it.
GitHub repository with 42 stars and 0 forks.
Language: Go
Topics: ai-gateway, aider, anthropic, claude-code, cursor, gguf, golang, inference, llama-cpp, llm