manifesto.md

Bundle 8 documents

Agentic Stack

What an agent request meets on its way to a system, in order.

  1. 1AGENTS.md

    A Markdown file at the root of a repository that gives AI coding agents the context and instructions a new teammate would need, kept separate from the human README.

  2. 2The /llms.txt file

    A proposal for a Markdown file at /llms.txt that gives language models a curated overview of a website and links to clean Markdown versions of its pages.

  3. claimed

    312-Factor AI-enabled CLI

    Twelve testable factors for a command-line tool whose operator may be a human or an AI agent, from machine-readable capabilities to meaningful exit codes, with a conformance gate.

    v0.1
  4. 4Model Context Protocol

    An open protocol, built on JSON-RPC, for connecting LLM applications to external data sources and tools through hosts, clients and servers.

    v2026-07-28 Agent State
  5. 5Agent2Agent Protocol

    An open protocol for communication and interoperability between opaque agentic applications, with JSON-RPC, gRPC and HTTP+JSON bindings and an Agent Card for discovery.

    v1.0.0
  6. claimed

    6Purpose-bound Access Control and Trust

    How an AI agent proves who it acts for, with what declared purpose and evidence, to a gateway that already authenticates and authorizes; a PACT pass never grants access and a native denial always wins.

    v1.0.0-alpha.0
  7. 7Agentic Permissions Policy Algebra

    A declarative policy format and deterministic engine that labels data flowing between an LLM agent and its tools, so restricted data cannot reach audiences it was never allowed to reach.

    vv0.37.0
  8. claimed

    8Agent Operation Protocol

    Six laws a system must enforce at its API boundary so that any actor, human or agent, can act on a shared operational graph without breaking it.

Other bundles