cygnus

koikar/cygnus

★ 0 stars Python AI/LLM Updated 7d ago

Antifragile control layer for robot arms — robots that get stronger from rare failures. SO-101 arm as an MCP server with a black-swan recovery + learning loop. EuroTech × HKTE Hackathon, AI & Robotics.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "cygnus": {
      "command": "uvx",
      "args": [
        "cygnus"
      ]
    }
  }
}

Or install with pip: pip install cygnus

README Excerpt

**An antifragile control layer for robot arms — robots that get *stronger* from rare failures.** Built for the **EuroTech × Hong Kong Talent Engage Hackathon** (Munich, June 2026) · **AI & Robotics** track. --- Most autonomous robots are *fragile*: they run beautifully on the happy path and fail catastrophically the first time reality hands them something they've never

Tools (20)

detect_colored_blocksget_capabilitiesget_ee_poseget_joint_effectsget_robot_modelget_stategriphomelookmove_ee_bymove_ee_tomove_relativemove_torelaxrun_sequencerun_skillsave_skillset_gripperset_speedwait_until_settled

cygnus

Quick Install

README Excerpt

Tools (20)

Related AI/LLM Servers