CI · Live showcase report · Python · License
Let's Bring Brain To Robots
Visible household-robot demos driven by MCP tools, reusable skills, and model-backed agent runtimes. Roboclaws makes each run reviewable through maps, frames, tool traces, scores, and public/private evaluation boundaries.
It answers three practical questions:
- How can an AI agent drive a robot?
- What context and tools does the agent need?
- What did the agent actually do in the simulated or robot-backed world?
Start with the live showcase report to see the latest model-backed and deterministic results. The showcase workflow owns the scheduled/manual CI runs and links each attempt to its artifacts.
For local execution, installation, command grammar, and provider setup, use just/README.md, model-matrix.md, and local-runtime.md.
The live showcase report is advisory evidence rebuilt from GitHub Actions. Each row is independent, and canonical bundles remain Actions artifacts.
| Demo | View the effect | CI definition |
|---|---|---|
| Deterministic smoke | Latest report | Smoke row |
| Map build | Latest report | Kimi row |
| Household cleanup | Latest report | Kimi / MiMo / MiniMax rows |
| Open household goal | Latest report | Kimi / MiMo / MiniMax rows |
The local operator console and maintainer gate
(just agent::verify) are documented separately.
- Architecture and operating modes
- Commands and verification
- Models and local runtime · keys and artifacts
- Current project status
- Human documentation index
MIT