Skillget

roboclaws

mcp
Security Audit
Fail
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in .github/workflows/ci.yml
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Visible AI-driven robotics demos powered by VLM policies, MCP skills, and AI coding agents. Reviewable HTML reports — frames, maps, tool traces, scores — instead of buried terminal logs.

README.md

Roboclaws

CI (main)
Live Reports
Python
Install
License

Let's Bring Brain To Robots

Visible household-robot demos driven by MCP tools, reusable skills, and live-agent SDK/direct runtimes.

Roboclaws is a thin demo repo for making AI-driven robotics behavior reviewable:
frames, maps, tool traces, scores, and public/private evaluation boundaries are
rendered as HTML reports instead of buried in terminal logs.

Surface, intent, skill, and capability profile architecture

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?

MCP and Skill Design Principles

Roboclaws treats reusable robot behavior as skills first and MCP tools as a
bounded public robot capability surface.

The short version:

  • Public runs use just run::surface with surface=..., optional
    preset=..., and natural-language prompt=....
  • Skills own task strategy such as map-build, cleanup, and open household
    goals.
  • MCP exposes bounded robot capabilities such as observe, navigate, pick,
    place, and done.
  • Private evaluator truth stays out of agent inputs and public profile
    metadata.

The detailed profile and skill reference is
docs/human/mcp-skills-and-semantic-profiles.md.

Run Demos With Just

Install the project once:

uv sync --extra dev

The dev extra includes the standard MolmoSpaces/MuJoCo CPU runtime used by
local cleanup demos. Isaac Lab is scoped to the B1 / Map 12 digital-twin route
and generic local runtime proof; keep it isolated in .venv-isaaclab/ and do
not treat it as part of normal MolmoSpaces demos.

The public command grammar is named-parameter only. Public household launches
name the operator-facing surface, world or scene, backend runtime, optional task
preset, and agent engine separately:

just run::surface surface=<surface> agent_engine=<engine> [world=<world>] [backend=<backend>] [preset=<preset>] [prompt=<goal>] [key=value ...]

For full command routing, profiles, and maintainer-only recipes, read
just/README.md.

To monitor and launch the supported local SDK household routes from a
standalone browser console, run:

just console::run

The console uses the same world/backend/preset/agent-engine catalog for local
SDK/direct runs, but its main screen is organized around product workflow
actions: Build Map, Open Task, and Cleanup. Runtime Map Prior Snapshot use is a
workflow setting, while standard mess preparation and reset are scene setup or
operations controls. Advanced controls expose raw launch axes for maintainers;
browser-submitted launches still resolve through the public catalog rather than
arbitrary shell commands.

Demo Matrix

The report site at miaodx.com/roboclaws is a
frozen historical archive. GitHub Actions no longer assembles or publishes it,
so current runs produce local artifacts and do not update archive links.

Demo Run it locally Report
Map build just run::surface surface=household-world world=molmospaces/procthor-10k-val/0 backend=mujoco preset=map-build agent_engine=openai-agents-sdk provider_profile=kimi-openai-chat evidence_lane=camera-grounded-labels camera_labeler=grounding-dino seed=7 scenario_setup=baseline Local artifact today. Use agent_engine=direct-runner only for deterministic contract baselines.
Household cleanup just run::surface surface=household-world world=molmospaces/procthor-10k-val/0 backend=mujoco preset=cleanup agent_engine=direct-runner evidence_lane=world-public-labels seed=7 scenario_setup=relocate-cleanup-related-objects relocation_count=5 Frozen historical Molmo live index
Open household goal just run::surface surface=household-world world=molmospaces/procthor-10k-val/0 backend=mujoco agent_engine=openai-agents-sdk provider_profile=kimi-openai-chat prompt="find something useful to drink" Local artifact today.
Planner proof just run::surface surface=planner-proof world=planner-proof/default backend=mujoco intent=planner-proof agent_engine=direct-runner mode=dry-run Local artifact today.
Operator console just console::run Local-only operator surface.
Maintainer gate just agent::verify CI status: workflow

See ARCHITECTURE.md for the code map and the full operating
mode contract.

Documentation Map

Need Read
Code map and operating modes ARCHITECTURE.md
Human setup/runbooks/domain docs docs/human/README.md
Detailed MCP profile reference docs/human/mcp-skills-and-semantic-profiles.md
Eval suites and validation docs/human/evaluation.md
Skill library convention skills/README.md
Public command grammar just/README.md
Local keys and report artifacts docs/human/local-runtime.md
MolmoSpaces settings docs/human/molmospaces-settings.md
Current project focus STATUS.md
Agent operating rules AGENTS.md

License

MIT

Reviews (0)

No results found