FROG is a fully open graphical dataflow language designed for secure, deterministic, and hardware-agnostic orchestration. With an open JSON expression, IR core, and multi-target compilers, FROG separates language, runtime, and IDE to create a true open foundation for graphical programming.

Semantic Emergent Syntax (SES) — spec v0.1 & reference snapshots

A decentralized protocol for agent trust, dialogue, and influence in open multi-agent systems.

Open packaging format for AI coding assistant extensions -- one archive installs skills, agents, MCP servers, and hooks across any compatible tool.

A normative specification for legible, inspectable digital infrastructure.

An open specification for AI Agent interaction with web applications using semantic HTML attributes (data-ai-*), JSON-LD policies, and standardized HTTP contracts.

airlock is a cryptographic handshake protocol for verifying AI model identity at runtime. It enables real-time attestation of model provenance, environment integrity, and agent authenticity - without relying on vendor trust or static manifests.

Open-source, offline-first reference model for transparent and auditable driver worktime calculation based on real operational data.

Concept & specs for a visual WFH status indicator for remote workers — to reduce interruptions in shared homes by showing when you're on a call, focused, or available. Open to community-driven development.

Open specification for user-sovereign encrypted data vaults — passwordless auth, per-quantum encryption, privacy by architecture.

AI-Me Vendor Card Specification — machine-readable, one-fetch site-wide discovery for AI agents

ACP: Open spec for AI agent-native data commerce. Three schemas — Agent Terms (ATS), Authorization Policy (AAP), Transaction Record (ATR) — enable agents to discover, evaluate, and transact with proprietary data sources autonomously. Python reference implementation included. Payment-rail agnostic.