Building OpenCastor
Declarative robotics
starts with
a manifest.
ROBOT.md is to a robot what CLAUDE.md is to a codebase.
One file — YAML frontmatter + markdown prose — so Claude Code, Claude Desktop, Cursor, Zed, Gemini CLI, or any MCP-aware
agent can safely operate the robot. I'm a one-person team building the spec, the runtimes, the surfaces, and the public
registry — almost entirely with Claude Code.
Try it on your robot
pip install robot-md robot-md-mcp
robot-md init --yes
The Ecosystem
Eleven repos. One stack.
A protocol at the bottom (RCAN), a manifest in the middle (robot-md), MCP and Agent SDK surfaces on top, a public registry on the side. Each layer is its own repo, its own release cadence, its own clear concern.
Method
Built with Claude Code
The point isn't that an LLM helped me write code. The point is that a one-person team — me — was able to ship and maintain a multi-repo ecosystem because Claude Code's long-context behavior made the cascade tractable.
A spec change in rcan-spec ripples through
rcan-py and
rcan-ts; a manifest schema change ripples through
robot-md, every consumer, and the registry. Claude Code holds
the context that would otherwise be split across a team.
The Anthropic-native bias of the surfaces — MCP server, Claude Code plugin marketplace, Agent SDK on the pendant and dispatcher, Claude as the exclusive eval model in autoresearch — is on purpose. Every Anthropic primitive gets a first-class surface.
By the numbers
April 2026 · single-person team
Hardware in the loop: a SO-ARM101 arm called bob, registered as RRN-000000000001.
Every shipped feature is exercised against real servos before merge.
Earlier work
Before robot-md
Computer vision, accessibility, and edge AI projects that informed the choices in OpenCastor.
LiveCaptionsXR
Spatial captions for XR collaboration. On-device speech recognition with anchored transcripts so deaf/HoH participants can follow conversations inside headsets.
Project page →BicycleRadar
Predictive collision avoidance for cyclists. Sensor fusion + ML produced 3.2-second warning windows at 96% prediction accuracy.
Project page →Dronevade
Edge computer-vision platform for drone detection. Custom YOLO models, RF + thermal fusion, designed for wildfire responders and utilities.
Project page →HeatCompass
Personal heat-stress monitoring for outdoor workers and athletes. Edge inference on a wrist-worn device.
Project page →Latest writing
From the build log
Shipped log: 2026 through mid-May
A topical roll-up of what shipped across the robot-md / OpenCastor ecosystem, the PlatAtlas / mcp-tape / mcp-replay family, and Heat Compass between January and 2026-05-19. Tables of versions, dates, and PR / release pointers. First dedicated coverage of Heat Compass on this site.
Four artifacts that externalize agent state
Agents arrive at each session without persistent state. Externalization mechanisms differ in what they capture: intent, declaration, structure, execution. Treating them as one bucket obscures the architectural choice in each. This post separates the four artifacts produced by the work shipped in 2026.
Notes on running two product families in parallel
Two distinct product families ship from this account in 2026. They share no source code, no authentication, no brand, and no roadmap. They share an operator. This post documents their structural shape, their repository topology, and the resolution rule between them.