specification

An open framework for scoring how well an MCP tool definition communicates to an AI agent, with a spec, reference implementation, CLI, and hosted API.

Open standard for product intent and evidence in AI agent-led software work. The repo includes a spec, parser/CLI tools, MCP server support, and loadable agent skills for writing, validating, and reconciling Product Specs.

Sightmap is an open YAML format and CLI for maintaining shared runtime context about a web app for AI agents. The repo includes the spec, reference Go implementation, docs, and agent skills for browser use and authoring.

Anthropic’s research preview introduces the Model Hardware Standard (MHS), a shared spec for AI agents to control physical devices and orchestrate lab or manufacturing equipment. The page explains how the standard works, shows early lab examples, and positions it as an upcoming open source standard for hardware integra

Canonical Agent Notation (CANON) is an open-source controlled English for model prompting and agent-to-agent communication. The repository describes a small closed vocabulary, mandatory obligation markers, bounded loops, and a clear ask-rather-than-guess rule for making requests and agent messages less ambiguous.

An open, code-first fork of the Model Context Protocol focused on keeping the spec permissionless and transparent. The repo includes the protocol spec, schema, docs, compatibility notes, and build instructions.

KillSwitch is an esoteric programming language aimed at breaking LLMs and coding agents. The site includes a language overview, interpreter/specification/examples, and benchmark references.

A draft specification for an offline emergency dispatch protocol designed for on-device AI models on phones when no dispatcher is available.