Ambient Desktop Docs
Quickstart Download ambient.xyz
Ambient Network

Local Models And Routing

Not every task should leave your machine. Ambient can route work across local runtimes, cloud models, and specialized providers — keeping private, cheap, or latency-sensitive work local while reserving heavy reasoning for the cloud.

In Development
Provider Priority And Fallback Search, scraping, browser, model, and media providers can be prioritized and retried according to user preference and task fit. Provider Priority And Fallback Search, scraping, browser, model, and media providers can be prioritized and retried according to user preference and task fit. orders choicesmatches taskclassifies resultrecords fallback Provider router preferencecapabilityfallback 1 Preference User orderPrivacy modeLocal firstCost awareness 2 Capability SearchFetchBrowserVision 3 Runtime result SuccessBlockedTimeoutPolicy denial 4 Fallback Next providerExplain skipRecord evidence
Search, scraping, browser, model, and media providers can be prioritized and retried according to user preference and task fit.
Product screenshots

Settings

Settings search keeps provider, permission, and runtime configuration discoverable.

Ambient Desktop settings search.

One task, the right model

A single model is rarely the right answer for every step of a task. Summarizing a private file, analyzing a screenshot, and reasoning through an architecture trade-off have different needs for privacy, latency, cost, and capability. Ambient treats the model layer like the provider layer: an ordered set of runtimes that can be selected and retried by what the task actually needs.

What can route where

On your machine

Local runtimes

llama.cpp-hosted models with non-destructive start/stop lifecycle, for private, low-cost, or offline-friendly work.

Vision, locally

MiniCPM-V

Local visual analysis so screenshots and images can be understood even when the selected text model has no native vision.

Heavy reasoning

Ambient & cloud

High-capability and network-native models for the hard synthesis steps a small local model should not own.

Coming

Ambient Mini

A future local-model network layer where eligible machines can serve and earn — built on this same runtime foundation.

Controls you have

  • Prioritize local-first, fastest, most private, cheapest, or most capable providers.
  • Disable a provider entirely so it never receives a class of content.
  • Inspect fallback and skip evidence to see why a given runtime was or was not used.
  • Repair or revalidate local runtimes from Settings when assets or binaries drift.

FAQ

How is this different from provider routing?

Provider routing covers search, fetch, browser, and vision capabilities; local model routing is the model layer specifically. They share the same idea: an ordered, retryable set chosen by preference and task fit. See Provider Priority and Dynamic Fallback.

Do I need a powerful machine?

Local runtimes scale with your hardware. You can keep heavy reasoning in the cloud and use local models for private, cheap, or vision tasks — or run more locally on capable machines.

Is this finished?

The runtime lifecycle, local-first selection, and vision routing are real today; broader routing across Ambient and Ambient Mini is still being built, which is why this page is labeled In Development.

Keep going

Use AmbientProvider RoutingAmbient can prioritize and fall back through providers for search, fetch, browser, media, and model-adjacent work.CapabilitiesLocal Visual AnalysisYour favorite text model might not see images. Ambient bridges that gap locally: it routes screenshots, images, and video frames to a MiniCPM-V vision model on your own machine and hands the agent structured observations back.Ambient NetworkMini MiningIf 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.