manifesto.md

Specificationvv0.37.0Agentic Stack

Agentic Permissions Policy Algebra (OpenAPPA)

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.

Labelled Preview and RFC by its authors; the policy file format is version 2 and the wire protocol version 1.

Canonical text: https://www.openappa.com/contracts, read against version v0.37.0.

Core concepts

  1. An OpenAPPA policy defines restrictions on tool results and requirements for tool calls.
  2. An audience identifies who can receive data.
  3. Trust describes how much OpenAPPA can rely on the data the agent has received.
  4. Effects record successful actions.
  5. Attention requires fresh approval for each call.
  6. An annotator classifies a tool call.
  7. A sanitizer cleans or validates data before an agent or tool receives it.
  8. An authority reviews a tool call that would otherwise be blocked.
  9. Remedy plans give the agent ways to continue when a call is blocked or a result would add restrictions.

Facts

Maintainer
Archestra.AI
Repository
https://github.com/archestra-ai/OpenAPPA
Licence of the text
MIT
First published
2026-08-18
Status of the text
draft
Listing
listed, not yet claimed

Read with

Badge

manifesto.md: listed

[![manifesto.md](https://img.shields.io/endpoint?url=https://manifesto.md/badge/openappa.json)](https://manifesto.md/openappa/)

Maintainers claim a listing with a pull request setting listing: claimed, or a yes on the listing issue.