agentleFS
Sign inStart free
sandraschisandraschi/bumi-mcp/llms.txt

bumi-mcp

llms.txt7 starsChanged 4 months agoMITView on GitHub

FastMCP 3.1 MCP for Noetix Bumi humanoid: hero specs, OSS/GitHub pointers, optional BUMI_ROBOT_URL health ping, virtual-twin composition map (resonite-mcp / robotics-mcp / worldlabs-mcp). No implied low-level motion API until vendor bridge is wired. Bumi vbot is composed from existing MCPs: robotics-mcp, resonite-mcp, unity3d-mcp, blender-mcp, worldlabs-mcp (+ avatar-mcp as needed). See knowledge.VIRTUAL_TWIN_FLEET and data/fleet_default.json.

The file

Create a free account to mount
Files
llms.txt
# bumi-mcp

> FastMCP 3.1 MCP for **Noetix Bumi** humanoid: hero specs, OSS/GitHub pointers, optional `BUMI_ROBOT_URL` health ping, virtual-twin composition map (resonite-mcp / robotics-mcp / worldlabs-mcp). No implied low-level motion API until vendor bridge is wired.

## Repo

- https://github.com/sandraschi/bumi-mcp

## Run

- stdio: `uv run python -m bumi_mcp` or `bumi-mcp` entrypoint
- HTTP: `uv run python -m bumi_mcp --serve` → API `10774`, MCP path `/mcp`
- Web: `web_sota/start.ps1` → Vite `10775` (proxies `/api`, `/mcp`)

## Tools

- `bumi(operation=...)` — info | specs | sdk_links | market (Noetix + China humbot + JD / tier-1 retail) | robot_status | virtual_twin | fleet_peers
- `bumi_agentic_workflow(goal)` — sampling (SEP-1577)
- Prompt: `bumi_quick_start`

## Fleet / vbot

Bumi vbot is **composed** from existing MCPs: robotics-mcp, resonite-mcp, unity3d-mcp, blender-mcp, worldlabs-mcp (+ avatar-mcp as needed). See `knowledge.VIRTUAL_TWIN_FLEET` and `data/fleet_default.json`.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free