Blog

Insights on AI engineering, computer vision, machine learning, and accessibility technology

Explore Topics

Latest Feature

May 12, 2026 • 12 min read

From CLAUDE.md to workflow-atlas: a year of planning patterns, then Dave Jeffery's tweet

How my planning stack across the OpenCastor ecosystem — CLAUDE.md, MEMORY, spec/plan docs, status files — kept hitting the same ceiling, and what changed when Dave Jeffery posted a prompt about a single-page HTML + JSON workflow visualizer. The result is workflow-atlas, a Claude Code plugin that sits next to CLAUDE.md as the graphical layer over the textual context Claude already reads.

Read Full Article

claude-code workflow-atlas claude.md

May 12, 2026

The map and the trace: shipping mcp-tape and mcp-replay

A few hours after writing about workflow-atlas as a context layer for Claude, I shipped the execution-layer companion. mcp-tape records every MCP JSON-RPC call your agent makes; mcpreplay.dev lets you read what happened. Open source, MIT, alpha.

3 min

claude-code mcp workflow-atlas +5

May 1, 2026

Compliance-bot: building a flagship robot-md agent on Anthropic Managed Agents

Anthropic launched Managed Agents (beta) — composable APIs for cloud-hosted vertical agents. The first one I'm building on top is Compliance-bot: hand it a robot repo, it returns five signed attestation packets ready for EU AI Act submission. Why this is the open-core wedge robot-md needed.

9 min

robot-md anthropic managed-agents +5

May 1, 2026

What the OpenCastor ecosystem can do today, and what compliance it meets

An honest inventory of what OpenCastor + robot-md + RRF actually do as of 2026-05-01, and the regulatory standards the stack lines up with — EU AI Act, post-quantum signing, RCAN protocol §22-26 attestation packets. What's shipped vs. what's framed-for-submission.

14 min

opencastor robot-md RCAN +5

May 1, 2026

Shipped this week: 3 PRs in OpenCastor + a redesigned robotmd.dev

Week of 2026-04-25 → 2026-05-01 — what landed across the OpenCastor ecosystem. Three pick_place silent-failure bugs closed (OpenCastor #879/#880/#881), the HiTL/AUTHORITY notify-wiring shipped, robot-md v1.4.0 landed with hot-plug + announce/confirm + self-attestation, RRF §27 went live and bob completed the first registry-attested submission, robotmd.dev got rebuilt across 4 robot-md PRs (~+8,750 lines, 14 routes), and issue #32 got squashed.

9 min

opencastor robot-md release +4

April 30, 2026

robot-md v1.4.0: plug a servo bus and Claude announces it

v1.4.0 ships three independent feature tracks that, together, change what registering a new piece of hardware feels like: hot-plug detection at the OS level, an announce/confirm UX over MCP that lets Claude talk the operator through the bind, and the first half of SP6's self-attestation loop — robots now sign their own spatial-intelligence scores with their RCAN apikey.

8 min

robot-md opencastor RCAN +5

April 29, 2026

OpenCastor: a year of building 'declarative robotics' with Claude Code

An introduction to the OpenCastor ecosystem — a single ROBOT.md manifest, runtimes in Python and TypeScript, an MCP server, a Claude Code plugin marketplace, a public registry with EU AI Act-aligned compliance endpoints, and the consumer-tier UX I've been focused on lately. Built almost entirely with Claude Code, on a SO-ARM101 arm I call bob.

8 min

opencastor robot-md robotics +5

April 24, 2026

Shipped: robot-md on the Claude Code plugin marketplace

A two-command install that wires your robot's ROBOT.md into any Claude Code session as structured MCP resources. Also: what RCAN and the Robot Registry Foundation do, and why this plugin belongs in Anthropic's hosted MCP catalog.

9 min

robot-md claude-code mcp +5

April 24, 2026

robot-md-dispatcher: when 'expose MCP remotely' is the wrong answer

External systems need to drive robots too. The obvious move is to put robot-md-mcp behind an HTTPS frontdoor. It works. It's the wrong shape. Here's the right one — a BYOK Claude Agent SDK dispatcher that runs on the robot host.

11 min

robot-md claude-agent-sdk robotics +4

April 21, 2026

Four Days, $1,216 of Opus: Measuring a Solo Robotics Sprint on Claude Code Max

Between April 17 and April 21, 2026 I shipped ROBOT.md v0.1 through v0.8, an MCP server, a hardware pendant with ESP32-C6 firmware, and the landing page at robotmd.dev — across 364 commits in five repositories. This post documents the resource envelope (tokens, cost, cache-hit rate, commit cadence) and compares the observed working style to Thariq Shihipar's published recommendations for the 1M context window.

21 min

robot-md opencastor claude +7

April 17, 2026

ROBOT.md: The Session-Start File for Every Agent That Drives a Robot

Introducing ROBOT.md — a single-file declaration at your robot's root that any agent harness (Claude Code, ChatGPT, Gemini, Ollama, your own) can read at session start. Vendor-neutral. Apache 2.0. Shipping v0.1 today.

8 min

robot-md opencastor rcan +4

March 31, 2026

We just shipped post-quantum cryptography for robot identity — here's why we couldn't wait

Two papers landed today that changed my confidence in q-day. I spent the afternoon implementing ML-DSA-65 across OpenCastor's stack before the fleet grows beyond my own two robots.

6 min

opencastor security post-quantum +2

March 30, 2026

Claude meets Bob: an AI agent controlling a physical robot via MCP

What happens when you give Claude Code direct, LoA-gated, RCAN-signed access to a physical robot via the Model Context Protocol.

2 min

opencastor mcp physical-ai +2

March 29, 2026

Teaching robots to speak MCP — and why the EU AI Act made us build it right

OpenCastor now exposes a full MCP server with LoA-gated tools. Any AI agent — Claude Code, Codex, Gemini, cron jobs — can command and observe robots through a single interface. Here's why we built it, and how compliance requirements shaped the design.

5 min

OpenCastor MCP Physical AI +3

March 29, 2026

Closing 17 RCAN v2.2 compliance gaps in one sprint

A systematic audit of the OpenCastor RCAN v2.2 implementation surfaced 17 gaps across CLI, gateway, SDKs, and the Flutter client. We closed all of them.

3 min

opencastor rcan physical-ai +2

March 26, 2026

Why I Built a Robot Communication Standard (and Why It Now Handles EU Law)

RCAN v2.1 shipped today. It's a robot protocol that now handles firmware attestation, supply chain transparency, multi-robot fleet authorization, and EU AI Act compliance. Here's the full story — what it does, why it exists, and what scenarios it actually solves.

7 min

RCAN OpenCastor Robotics +3

March 20, 2026

Contribute: What If Every Idle Robot Ran Science?

OpenCastor's new contribute feature turns idle robot compute into a distributed science network. How the open-source runtime layer between robots and AI makes this possible, what RCAN is, and why a robot registry matters.

8 min

OpenCastor Robotics Distributed Computing +4

March 20, 2026

Gated Model Providers: Connecting Robots to Frontier AI

OpenCastor v2026.3.20.3 adds first-class support for authenticated access to closed AI models — Physical Intelligence π0, HuggingFace gated models, enterprise APIs, and more.

4 min

opencastor rcan robotics +2

March 20, 2026

OpenCastor is becoming a California Benefit Corporation — here's why that matters

Why we're structuring OpenCastor as a B Corp, how Castor Credits turn idle robot compute into real value, and why the RCAN protocol and Robot Registry need to be owned by foundations — not us.

9 min

opencastor rcan robotics +3

March 20, 2026

The Robot That Tunes Itself: OpenCastor's Harness Optimizer

How a nightly Gemini-powered research pipeline finds the best agent harness configuration for your robot — and why the next version will tune itself differently for every hardware profile.

4 min

opencastor ai robotics +1

March 17, 2026

RCAN v1.5: Making Robot-to-Robot Communication Production-Safe

Today we shipped RCAN v1.5 — addressing 18 security and safety gaps identified in a comprehensive protocol audit. Replay attack prevention, robot identity revocation, training data consent (EU AI Act), delegation chains, and more.

5 min

rcan opencastor robotics +2

March 17, 2026

RCAN v1.6: Four Hard Problems in Robot Communication

RCAN v1.6 ships the four gaps we deferred from v1.5: federated consent across registries, bandwidth-constrained transport (32-byte ESTOP for LoRa), multi-modal payloads with SHA-256 audit trails, and human identity verification with Level of Assurance.

4 min

rcan opencastor robotics +3

March 15, 2026

How I Got My Two Robots to Talk to Each Other

A detailed walkthrough of the full stack — OpenCastor, RCAN, LLM providers, Protocol 66 safety — behind two Raspberry Pi 5s holding a genuine planning conversation and coordinating on a real task.

12 min

opencastor rcan robotics +6

March 12, 2026

OpenCastor v2026.3.12.0: Smarter Hardware Detection

Four new hardware detectors and an expanded I2C lookup table land in OpenCastor v2026.3.12.0 — Dynamixel U2D2, RPLidar/YDLIDAR, Raspberry Pi AI Camera, LeRobot SO-ARM101, plus five new I2C sensor types.

6 min

opencastor hardware robotics +1

March 12, 2026

Presence Over Commits: Time Management for Dads in the Agentic Era

The closer AGI feels, the less we sleep. But the kids don't care about your PR queue. Here's how to build a clean agentic system that works while you're present — not one that steals your presence from you.

13 min

productivity parenting ai +4

March 12, 2026

The Robot Identity Stack: RCAN v1.3, OpenCastor, and the Robot Registry Foundation

Three projects. One complete open stack for robot identity, accountability, and registration. Here's what shipped and why it matters.

7 min

rcan opencastor robotics +2

March 11, 2026

OpenCastor v2026.3.11.0: Plug-and-Play Hardware Detection + LeRobot Support

castor scan now auto-detects 12+ hardware types. Plus native support for SO-ARM101, Koch arm, ALOHA, and Pollen Robotics Reachy.

5 min

opencastor robotics hardware +3

March 11, 2026

OpenCastor v2026.3.11.1: Making the Install Experience Not Terrible

Sixteen issues from a fresh Pi reinstall, now fixed. castor scan, doctor, upgrade, stop, gateway hardening, and a proper venv guide.

5 min

opencastor raspberry-pi robotics +1

March 10, 2026

OpenCastor v2026.3.10.1: Semantic Perception + Real Hardware

Two major additions ship today: an EmbeddingInterpreter that gives robots semantic memory using local CLIP embeddings, and first-class support for HLaboratories' ACB v2.0 BLDC motor controller.

8 min

OpenCastor Robotics Embeddings +3

March 6, 2026

The RCAN Ecosystem: Python SDK, TypeScript SDK, and OpenCastor v2026.3.6.0

Three simultaneous releases ship a complete open-source stack for AI-accountable robotics: rcan-py v0.1.0 on PyPI, @continuonai/rcan-ts v0.1.0 on npm, and OpenCastor v2026.3.6.0 with deep RCAN v1.2 integration.

5 min

RCAN Robotics AI Safety +2

March 6, 2026

March 6: The RCAN Full Stack Ships — SDKs, Swarm Safety, and a Distributed Registry

rcan-py v0.3.0, rcan-ts v0.3.0, OpenCastor v2026.3.8.0, §17 Distributed Registry, and RCAN-Swarm Safety — across four repos and most of the day.

8 min

rcan robotics ai safety +4

March 6, 2026

A Full Day of Building: RCAN Swarm Safety, §17 Distributed Registry, and What the Robot Registry Foundation Needs to Become Real

Coordinated releases across four repos, green CI on all of them, a new swarm safety claim for OpenCastor, and the clearest picture yet of what the Robot Registry Foundation actually needs to function.

12 min

RCAN Robotics AI Safety +4

March 4, 2026

Why You Should Adopt RCAN Before You Need To

Every robot incident investigation starts the same way: what did it do, who authorized it, and can you prove it? RCAN is the protocol layer that makes those questions answerable — before the incident happens.

8 min

RCAN Robotics AI Safety +4

March 4, 2026

RCAN: The Case for Robot Accountability Before You Need It

Why AI robots need accountability protocols now, what existing safety standards miss, and how to adopt RCAN before the incident that makes it mandatory.

10 min

rcan robotics safety +2

March 3, 2026

If We Start From a Safety Standard, We Can Build Faster

The automotive industry spent decades standardizing autonomy after the technology was already deployed. Robotics is at the same inflection point. RCAN, OpenCastor, and QuantumLink-Sim are a bet on doing it the other way around.

13 min

RCAN Robotics AI Safety +5

March 3, 2026

The Safety Standards Landscape for AI Robots

ISO 10218, OPC UA, IEC 62443, ROS2 — the standards that govern industrial robots today were written before AI was making the decisions. Here's what each covers, where they stop, and where RCAN fits.

10 min

RCAN Standards ISO +3

March 2, 2026

Sound is Stress: Identity, Silence, and the Echoes of History

A memoir weaving together a life between the Deaf and hearing worlds with the dangers of divisive rhetoric—and why 'us versus them' hits differently when you've lived between worlds your whole life.

22 min

memoir deaf identity +4

February 27, 2026

OpenCastor Is an Agent Harness

Thariq Shihipar from Anthropic published a detailed breakdown of how they built Claude Code. Every design decision maps to OpenCastor — but for a different consequence space. And this week, that consequence space got a lot more political.

19 min

OpenCastor Robotics AI Agents +5

February 27, 2026

Why I Added Quantum Cryptography to My Robot

AI agents make claims. Those claims drive actions. If you can't verify the chain — what was claimed, when, and under what keys — you can't audit anything. Here's how quantum-link-sim's CommitmentEngine solves that.

8 min

OpenCastor Robotics Cryptography +4

February 27, 2026

The Architecture of My Side Projects

Why I build things outside of work — and how I keep it sustainable.

5 min

Side Projects Career Work-Life Balance +1

February 26, 2026

OpenCastor Full History: From v2026.2.17.3 to v2026.2.26.2

A full-history technical timeline of OpenCastor from project launch on February 17, 2026 through v2026.2.26.2, including hardware, providers, swarm systems, and tutorials.

6 min

OpenCastor Robotics Runtime AI Providers +4

February 20, 2026

The Order of Operations Toward Swarm Intelligence

Why a robot that improves itself matters more than a fleet of static ones — and the engineering steps to get there.

5 min

OpenCastor AI Robotics +2

February 19, 2026

Introducing OpenCastor: The Universal Runtime for Embodied AI

Today we release OpenCastor v2026.2.19.0 — an open-source framework that connects any AI model to any robot hardware through a single YAML config. 7 providers, tiered brain architecture, Hailo-8 NPU vision, and a $0 starting cost.

7 min

OpenCastor Robotics AI +3

February 16, 2026

How Agent Decision Logging Solved My 60,000-Reference Problem

VS Code + Claude Code maintained context across weeks of SharePoint term store fixes through persistent memory files. Here's why decision routing matters more than token windows.

9 min

Claude Code AI SharePoint +3

February 14, 2026

Building LiveCaptionsXR with Nexa AI and Qualcomm's QDC Test Environment

How we integrated Nexa SDK for NPU-accelerated on-device AI and validated performance on Qualcomm Developer Cloud, achieving 2x faster inference and 9x better energy efficiency for real-time spatial captions.

7 min

LiveCaptionsXR Nexa AI Qualcomm +5

January 28, 2026

Sound is Stress: Identity, Silence, and the Echoes of History

16 min

memoir deaf identity +4

January 27, 2026

How We Reorganized an Entire AI Robotics Codebase in One Morning — With AI

ContinuonOS went from a chatbot wrapper to a complete cognitive architecture in 7 phases, all executed by Claude, Clawdbot, and Gemini working together on a Raspberry Pi 5. Here's how the architecture works, what we tested, and the principles that guide a robot brain designed to live with humans.

15 min

ContinuonAI ContinuonOS Robotics +7

January 26, 2026

Building the ContinuonXR Physical Robot: A Complete Parts Guide and Lessons Learned

A detailed breakdown of the parts, Bill of Materials, and grey areas we discovered while building a 6-foot-reach mobile manipulation robot with dual arms, V-slot mast, and EcoFlow power system.

14 min

ContinuonAI Robotics Hardware +5

January 23, 2026

Building an Autonomous Robot Learning Pipeline: From Training Games to Neural Networks

How we built a self-improving training system for ContinuonXR that generates its own learning curriculum, tracks brain state, and prepares data for MambaWave neural networks—all without human intervention.

9 min

ContinuonAI Machine Learning Robotics +4

January 23, 2026

CrowdTalkie Goes Offline: LoRa Integration, Command Center, and Twin Cities Rapid Response

How we extended CrowdTalkie with LoRa mesh networking, a decentralized Command Center for incident command, license plate OCR, photo geo-tagging, and zone handoff protocols.

10 min

CrowdTalkie LoRa Meshtastic +8

January 21, 2026

CrowdTalkie Development Update: Mesh Hardware, P2P Stability, and What's Next

A progress report on CrowdTalkie's evolution—from new mesh hardware guides to P2P networking fixes, CI/CD infrastructure, and a direction toward hardware-enhanced resilience.

6 min

CrowdTalkie Mesh Networking LoRa +6

January 19, 2026

From Flash Protest to CrowdTalkie: Building a Privacy-First Mesh Network for Crowd Coordination

How we evolved Flash Protest PTT into CrowdTalkie - a decentralized, end-to-end encrypted push-to-talk system built on libp2p mesh networking with Web Bluetooth fallback.

5 min

CrowdTalkie libp2p WebRTC +6

January 17, 2026

Flash Protest: A Free Push-to-Talk Tool for Rapid Community Coordination

The Antifascist Fun Brigade launches a web-based, mobile-first push-to-talk system for flash protests—no login required, geofenced rooms, and built for community safety.

8 min

Flash Protest Community Safety Push-to-Talk +6

January 15, 2026

Closing Civqo After 11 Days: The Actor Runtime and Why I'm Returning to ContinuonAI

Vibefounding makes startups easier to start—and easier to kill. Here's what I learned from 11 days building Civqo and why the missing runtime layer matters.

16 min

Civqo ContinuonAI Actor Runtime +6

January 15, 2026

Building a Documentary with AI: 15 Atmospheric Clips from Veo 3.1

A complete toolkit for generating atmospheric video backgrounds using Google's Veo 3.1 AI model, designed for quote-based political documentaries.

8 min

AI Veo video generation +3

January 14, 2026

From Executive Order to Tragedy: The Escalation That Killed Renee Good

A 353-day timeline from immigration executive orders to the killing of a U.S. citizen in Minneapolis, examining historical patterns of authoritarian escalation and documented threats to the 2026 elections.

23 min

politics democracy history +2

January 14, 2026

In His Own Words: A Chronology of Authoritarian Rhetoric

Donald Trump's trajectory from unconventional candidate to second-term president traced through his own verified, sourced statements spanning 2018-2026.

21 min

politics democracy documentation +1

January 14, 2026

Introducing MeloMax: Reclaiming Attention

Meet MeloMax, an app built to reduce doomscrolling and rebuild attention spans. Free, private, and local with no auth required.

2 min

MeloMax Attention Focus +4

January 14, 2026

Making of the Veo Documentary

Behind the scenes of creating an atmospheric documentary using Google's Veo 3.1 model.

2 min

AI Video Generation Veo +2

January 14, 2026

Vladimir Putin's 25-Year Campaign to Reshape Global Order

From KGB officer to Kremlin master: How Putin transformed Russia into a revanchist power waging war on its neighbors while cultivating unprecedented influence over American foreign policy.

15 min

politics Russia history +2

January 12, 2026

Ralph: Cross-Platform Autonomous AI Development, Now Open Source

Geoffrey Huntley's Ralph Wiggum technique for every platform. macOS, Windows, Linux, Raspberry Pi, and cloud servers. 10+ AI agents for autonomous coding.

5 min

Ralph Loop Claude Code AI +7

January 12, 2026

Why AI Agents Can Now Build Silently for Hours

A breakthrough in AI agent architecture means you can now send a single prompt and let an agent build autonomously for hours—without the degradation that previously made long sessions unreliable.

6 min

AI Agents Development +2

January 11, 2026

From Claude Code to Civqo: 7 Days, Nights Only

182 commits after the kids went to bed. A cloud platform built with Claude Code and the Ralph Loop.

4 min

Claude Code AI Vibe Coding +6

January 5, 2026

Part 6: The RCAN Spec Repository and Website

A deep dive into the RCAN open source project, its Astro-based architecture, and how you can contribute to the future of robot communication.

3 min

Robotics RCAN Open Source +2

January 3, 2026

The RCAN Technical Specification: JSON Schemas and Protobufs (Part 5)

The technical appendix to the RCAN protocol proposal. Includes JSON Schema for Robot URIs, Protocol Buffer definitions, and a complete handshake flow—proving RCAN is real code, not just a blog post.

19 min

Robotics AI Protocol +5

January 2, 2026

We Need an ICANN for Robotics: Introducing RCAN (Part 4)

The internet has ICANN. IoT has Matter. Robotics has nothing. The RCAN protocol proposes a global addressing, authentication, and governance standard for embodied AI.

9 min

Robotics AI Governance +4

December 31, 2025

My 2025 Year in Vibe Coding

2,652 commits, 76 new projects, and the journey from chasing business ideas to just building.

7 min

Vibe Coding AI Year in Review +4

December 29, 2025

When Robots Carry Values (Part 1)

China's dominance in industrial robotics raises fundamental questions about who shapes the values embedded in embodied AI systems that will increasingly act in the physical world.

5 min

Robotics AI China +4

December 29, 2025

We Need a Constitution for the Robot Age (Part 2)

As embodied AI scales, we need a governance stack for the physical world—a constitutional operating system that encodes safety, law, and social norms into every robot's decision-making framework.

4 min

Robotics AI Governance +4

December 29, 2025

One Brain, Many Shells: Applying the UNIX Philosophy to Embodied AI (Part 3)

Why the future of robotics isn't a better robot—it's a better Operating System. How ContinuonAI applies UNIX principles to build the operating system for embodied AI.

5 min

ContinuonAI Robotics UNIX +4

December 9, 2025

Design Rationale for Non-Overridable System Instructions

A technical rationale for the latest Continuon Brain defaults: why they are explicit, how they resolve multi-owner conflicts, and how they preserve safety without degrading swarm throughput.

3 min

Continuon Brain Robotics Safety +2

December 8, 2025

Why the ContinuonAI Experiments Feel Different

Testing hypotheses about safety-first autonomy, reproducible robot builds, and what happens when a cognitive architecture lives at the edge instead of the cloud.

12 min

ContinuonAI ContinuonAI Robotics +3

December 2, 2025