Lumoswitch Docs

Lumoswitch · Agent console & AI toolbox

Get your AI tools ready

Start in the desktop app: connect a model, configure an Agent or open a workspace. Add Skills, MCP and optional companions when you need them.

Using the cloud API? The console, upstream and API references remain available in the sidebar. Older manual Agent instructions remain accessible and are marked Deprecated.

Earlier cloud introduction (retained)

Lumoswitch Docs

Lumoswitch is an AI console that brings models and agents together. One access key can call multiple models. The desktop client helps automatically install and configure agents and lets you add Skills as needed. Review and confirm changes before applying them.

One key to rule them all.

Start here

  • Quickstart: create a configuration and make your first Lumoswitch request.
  • Upstreams: add provider keys or local model servers.
  • API configurations: choose a routing mode and issue an access key.
  • Agent setup: choose a coding Agent and review one-time, persistent, and removal modes.
  • API reference: review the public inference routes and the Lumoswitch control API.

Core capabilities

CapabilityDescription
Unified inferenceClients call one stable Lumoswitch endpoint
Multiple upstreamsConnect cloud and local models with provider presets or a custom OpenAI-compatible URL
Runtime routingLumoswitch executes fixed, failover, auto, least-busy, and lowest-latency configurations
One key, multiple modelsOne access key calls the models published in its configuration

New users should begin with the Lumoswitch quickstart.