Install
Native Windows, Ubuntu, and macOS applications enroll your device using an outbound encrypted connection.
TOKEN2TOKEN CLIENT
Idle silicon should work for you.
Connect an existing local engine or use a managed runtime. Choose models, publish your price, cap monthly Indigo, and stop at any time.
Detect
Models from Ollama, LM Studio, llama.cpp, and vLLM are discovered and tested automatically.
Earn
Set input/output rates and receive 95% of every verified generation as Indigo.
Know the boundary. Community hardware is not confidential compute. Sensitive requests belong on contractually protected Official endpoints.