◆ Local Language Machine
All-in-one, fully offline AI coding — self-contained inference, zero external services.
A complete AI coding IDE that runs entirely on your own machine. The model runs in-process; your code never leaves the device. No API key, no account, no network dependency. Open a folder, load a model, and start pairing.
Get started in three commands
# requires Node ≥ 22 — GPU used automatically when present git clone https://github.com/siroxou/local-language-machine.git cd local-language-machine npm install npm run preview
The inference engine is bundled — no extra services. On first run, load a model from the Assistant panel; it downloads once and caches locally.
🔒 Private by designInference runs in-process. Files and prompts stay on disk.
⚡ Fast turnsLive KV cache — each turn only evaluates new tokens.
🧩 Real agentReads, edits, greps, runs commands through a permissioned tool loop.
🎓 On-device tuningBuilt-in LoRA training and evaluation — MLX or Unsloth.