Documentation

Everything you need to run Keikaku on your own hardware and connect it to your cloud. Start with the self-hosted agent guide; benchmark your GPU first if you're unsure which model to run.

Self-hosted agents

• Run a self-hosted agent Architecture, prerequisites, and the end-to-end setup steps.
• Benchmark your GPU Measure real models on your hardware and get a recommendation.

Set up your machine

• Windows Docker Desktop + Ollama on an NVIDIA GPU.
• Linux Docker Engine + Ollama, with the host-gateway note.
• Choosing a model What fits your VRAM, and the CPU fallback.