Skip to content
View snapsynapse's full-sized avatar
6 followers · 4 following

Highlights

  • Pro

Block or report snapsynapse

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
snapsynapse/README.md

Sam Rogers

Building open infrastructure for human-AI collaboration. Founder & CEO, PAICE.work · President, Snap Synapse

AI adoption breaks at the seams between roles, decisions, and operating models. I build measurement frameworks, open protocols, and agent tooling that make collaboration between humans and AI systems structurally sound — not just technically possible.

Current focus: PAICE behavioral diagnostics for People+AI Collaboration Effectiveness.

What I'm building

Open standards and tooling released independently from PAICE because interoperability is the point, not lock-in.

Protocols & specifications

Project What it does
graceful-boundaries Spec for how services communicate operational limits and error context to humans and autonomous agents
turnfile File-based protocol for LLM agents to collaborate on shared codebases without real-time communication
hardguard25 25-character alphabet for human-friendly unique IDs — like Crockford Base32 minus 11 confusable characters

Agent skills

Project What it does
skill-provenance Metaskill for version-tracking agent skill bundles across sessions, surfaces, and platforms
skill-a11y-audit Drop-in WCAG 2.1 AA accessibility audit for Claude Code, Codex, and other AI coding agents

Knowledge as Code

Project What it does
Knowledge as Code Pattern and template for building structured knowledge bases that generate static sites, JSON APIs, and multi-output from markdown
Every AI Law Which AI regulations you likely care about, and why. Structured, obligation-first reference for compliance teams, legal counsel, and AI agents.
AI Tool Watch Plain-English reference for what AI tools can actually do — capabilities, pricing, and platform support across ChatGPT, Claude, Gemini, Copilot, and more
Virtual Meeting Reference Structured reference tracking capabilities across 22 virtual meeting and classroom platforms

Tools & contributions

Project What it does
Siteline Public scanner that grades whether a website presents a usable path for AI agents acting on behalf of humans
substack2md Convert Substack newsletters to markdown for local libraries and consistent RAG storage
paice-near-integration Privacy-preserving AI collaboration scoring with verifiable inference and on-chain attestation via NEAR
OB1 Contributor to Nate B Jones' Open Brain — the infrastructure layer for your thinking

Elsewhere

Pinned Loading

  1. graceful-boundaries graceful-boundaries Public

    A specification for how services communicate operational limits and error context to humans and autonomous agents.

    4

  2. skill-provenance skill-provenance Public

    Finally a source of truth for agent skill bundles! Use this metaskill for version tracking across sessions, surfaces, and platforms. Tracks identity, staleness, and intent inside the bundle.

    Shell 3 1

  3. ai-tool-watch ai-tool-watch Public

    Evidence-backed reference for AI capabilities, pricing tiers, availability, and platform support across ChatGPT, Claude, Gemini, Copilot, and more.

    JavaScript 7

  4. turnfile turnfile Public

    file-based protocol for making LLM agents collaborate on shared codebases without real-time communication

    JavaScript 5

  5. skill-a11y-audit skill-a11y-audit Public

    Drop-in accessibility audit for AI coding agents. WCAG 2.1 AA scanning with template-aware sampling, remediation hints, and progress tracking.

    JavaScript 1

  6. hardguard25 hardguard25 Public

    A 25-character alphabet for human-friendly unique IDs. Like Crockford Base32, but removes 11 confusable characters instead of 4.

    JavaScript