Developer tool
NanoLM
Run local AI models with one binary and OpenAI-compatible APIs.
v1.0 · Beta · Windows · macOS · Linux
About
A lightweight local AI runtime written in Go. NanoLM manages GGUF models, serves an OpenAI-compatible HTTP API, and wraps llama.cpp — so any tool that speaks the OpenAI API can run against models on your own hardware.
Highlights
✓ Single binary — no Python environment, no dependency hell
✓ OpenAI-compatible API: drop-in for existing SDKs and tools
✓ Downloads, verifies, and manages GGUF models
✓ Powers Sentrize Coder and any local-AI workflow
Built with
Gollama.cppGGUF
Questions about this product?
We answer fast — licensing, roadmap, enterprise deployment, or anything else. Contact us.