automation

Rosclaw: Automate robot tasks

Streamline robotics development with rosclaw, a self-evolving runtime infrastructure for Physical AI and embodied agents, useful for founders in robotics and
186 stars33 forksPythonGuide quality 8/10Updated 8/24/2026100% free · open source
What it does

Rosclaw streamlines robotics development by providing a self-evolving runtime infrastructure for Physical AI and embodied agents, allowing founders to ground AI agents into robot bodies

When to use it
  • When developing robotics applications that require integration with physical agents
  • When needing to evolve AI capabilities in real-time through physical interactions
  • When requiring a sandboxed environment for safe testing of robotics applications
Ready-to-paste prompt
python rosclaw/examples/e_urdf_example.py -u <robot_urdf_file> -c <capability_config_file>
Heads up: Rosclaw requires a compatible Python version and ROS (Robot Operating System) installation, ensure you have the correct versions installed before attempting to use rosclaw
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/rosclaw && curl -fsSL https://workflowstacks.com/api/skills/rosclaw/claude-skill -o ~/.claude/skills/rosclaw/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Rosclaw: Automate robot tasks works
Codeflow
Free to inspect

Rosclaw: Automate robot tasks is a very large Python project (~339k lines across 1587 code files, plus 1038 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~339k lines · 1587 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python · Docker
No API keys detected
Python 95%TypeScript 4%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/rosclaw
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    src/powermem/__init__.py
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic1382 files
packages/Sub-packages / plugins162 files
bin/Command-line entry points1 files
docs/Documentation194 files
examples/Examples you can copy165 files
tutorials/Examples you can copy3 files
data/Data files361 files
e-urdf-zoo/Folder248 files
READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month
Quick Actions
Details
Creator
ros-claw
Language
Python
Category
automation
Published
3/16/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.