jina-ai/jina-on-prem

OffGrid LLM is a production-ready, self-contained LLM orchestrator designed for environments with limited or no internet connectivity. Deploy powerful language models on edge devices, ships, remote clinics, factories, and air-gapped networks.

Your AI intranet: network the computers you already own for inference and training.

Local-first AI toolkit for the modern web. Build privacy-first AI applications that work entirely in the browser.

Local AI API Platform

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GPUs, one gateway. Powered by Ray Serve.

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V

Local inference, optimized for your hardware

TinyToT — Tree of Thoughts inference server