Ambient Mini Mining
If your machine is already running local models, it could do useful work for the network when you are not. Ambient Mini mining is a planned, opt-in way to host a local model and earn network rewards when eligible.
Settings
Settings search keeps provider, permission, and runtime configuration discoverable.
The idea
Ambient already manages local model runtimes for your own tasks. Mini mining extends that: with your explicit consent, an eligible machine can serve a local model to the network and earn rewards for the work it does. It is opt-in by design — nothing mines unless you set a machine-level mineable flag and accept the resource, privacy, and uptime implications.
How opting in is meant to work
Opt in
Mark a machine as mineable and set a resource policy and privacy boundary. Off by default; you choose when and how much.
Host
Ambient serves a local model through its managed llama.cpp runtime, with health checks keeping the host honest.
Route
When the machine is eligible, the network routes appropriate requests to it based on availability and policy.
Reward
Completed work produces receipts and network rewards, with operator controls to pause or stop.
Why the foundation already exists
Mining is on the roadmap, but it is not starting from zero. The runtime layer Ambient ships today is the same layer mining will stand on.
- llama.cpp hosting and non-destructive start/stop lifecycle management.
- Local runtime inventory, health checks, and repair flows.
- Provider routing and local-first model selection.
- Network-client direction for reward receipts and operator controls.
An honest word on rewards
This page says earn network rewards, and it deliberately stops there. It does not promise a fixed payout, guaranteed income, or final token economics — those depend on the public network contract, which is not finalized. Mini mining is labeled Roadmap, and these docs will sharpen the specifics as implementation and the network design catch up.