Drop an idea in a text file. Get back a verified, working repo. Localsmith chains your local and cloud LLMs to ship small projects unattended — routing the free work to your own GPU and spending cash only on the one step that needs it. Your code never leaves your LAN.
A small, auditable pipeline — no LangGraph, no Temporal, no cloud control plane. Just state.json per project and a resumable bash driver.
Cloud agents meter every token. Localsmith pushes scaffolding, planning and review to models you already run — cash is spent only on implementation. Real runs cost ~1–2¢.
Prompts and source never have to leave your LAN. Run fully local, or bring your own keys. Nothing is sent to us — there is no "us" server.
Stdlib Python + bash. One JSONL cost ledger. Resumable, idempotent, 27 tests. You can read the whole thing in an afternoon.
Wires straight into Ollama, LM Studio, and SearXNG. Ships with a one-command setup wizard that detects your local models.
The engine is free and open. Pay for the parts that save you the most time.
Open source · self-host
Lifetime, for the first cohort
Add-on · one-time