Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions .github/workflows/sync_version.py
Original file line number Diff line number Diff line change
Expand Up @@ -42,13 +42,13 @@ def main():
f.write(updated_content)
print(f"✓ Updated specification.md to version {version}")

# Update aos_schema.json
with open('specification/AOS/aos_schema.json', 'r') as f:
# Update acs_schema.json
with open('specification/ACS/acs_schema.json', 'r') as f:
data = json.load(f)
data['version'] = version
with open('specification/AOS/aos_schema.json', 'w') as f:
with open('specification/ACS/acs_schema.json', 'w') as f:
json.dump(data, f, indent=4)
print(f"✓ Updated aos_schema.json to version {version}")
print(f"✓ Updated acs_schema.json to version {version}")


if __name__ == "__main__":
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/sync_version.yml
Original file line number Diff line number Diff line change
Expand Up @@ -70,13 +70,13 @@ jobs:
Updated files:
- `pyproject.toml`
- `docs/spec/instrument/specification.md`
- `specification/AOS/aos_schema.json`
- `specification/ACS/acs_schema.json`

The version was read from the `version.txt` file.
branch: version-sync-${{ env.VERSION }}
delete-branch: true
add-paths: |
pyproject.toml
docs/spec/instrument/specification.md
specification/AOS/aos_schema.json
specification/ACS/acs_schema.json

14 changes: 7 additions & 7 deletions CLAUDE.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ Before finalizing any text, review against the Editorial Checklist in STYLE.md.

## Project Overview

AOS (Agent Observability Standard) is the industry standard for building secure, observable AI agents. It delivers three core capabilities:
ACS (Agent Control Standard) is the industry standard for building secure, observable AI agents. It delivers three core capabilities:
- **Inspectability**: Complete visibility into agent components and capabilities
- **Traceability**: Full trace trail with reasoning chains
- **Instrumentability**: Hard controls and policy enforcement
Expand All @@ -35,7 +35,7 @@ uv pip install -e .
## Architecture Overview

### Core Framework Components
The AOS framework consists of three interconnected layers:
The ACS framework consists of three interconnected layers:

1. **Instrument Layer** (Hooks)
- Real-time control points that allow Guardian Agents to permit, deny, or modify agent actions
Expand All @@ -56,8 +56,8 @@ The AOS framework consists of three interconnected layers:
- Critical for supply chain security and compliance

### Key Protocol Concepts
- **Observed Agent**: The AI agent being monitored (implements AOS endpoints)
- **Guardian Agent**: Enforces security policies and observability (consumes AOS data)
- **Observed Agent**: The AI agent being monitored (implements ACS endpoints)
- **Guardian Agent**: Enforces security policies and observability (consumes ACS data)
- **Session**: Scoped interaction unit from activation to completion
- **Step**: Atomic action/decision within agent reasoning process
- **Hook Response**: Guardian's permit/deny/modify decision with optional mutations
Expand All @@ -72,12 +72,12 @@ The AOS framework consists of three interconnected layers:
- **Standards Integration**: OpenTelemetry spans, OCSF events, SBOM formats

### Important Files
- `specification/AOS/aos_schema.json`: Complete JSON Schema for AOS protocol
- `specification/ACS/acs_schema.json`: Complete JSON Schema for ACS protocol
- `docs/spec/instrument/specification.md`: Detailed protocol specification
- `docs/spec/instrument/hooks.md`: Available hooks and their triggers
- `docs/spec/trace/events.md`: Event catalog and schemas
- `docs/topics/core_concepts.md`: Fundamental concepts and terminology
- `docs/topics/AOS_in_action_example.md`: Step-by-step implementation example
- `docs/topics/ACS_in_action_example.md`: Step-by-step implementation example
- `mkdocs.yml`: Documentation site configuration

### Navigation Structure
Expand All @@ -90,7 +90,7 @@ The documentation follows this hierarchy:
This is a documentation-focused project built with:
- **UV** for Python dependency management (replaces pip)
- **MkDocs Material** for documentation generation
- **GitHub Pages** for hosting at aos.owasp.org
- **GitHub Pages** for hosting at agentcontrolstandard.org

### Roadmap Context
- **v0.1** (Current): Documentation, schemas, and requirements
Expand Down
2 changes: 1 addition & 1 deletion CODE_OF_CONDUCT.md
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@ further defined and clarified by project maintainers.
## Enforcement

Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported by contacting the project team at [aos@zenity.io](mailto:aos@zenity.io). All
reported by contacting the project team at [acs@zenity.io](mailto:acs@zenity.io). All
complaints will be reviewed and investigated and will result in a response that
is deemed necessary and appropriate to the circumstances. The project team is
obligated to maintain confidentiality with regard to the reporter of an incident.
Expand Down
12 changes: 6 additions & 6 deletions CONTRIBUTING.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Contributing to AOS
# Contributing to ACS

We're building trustworthy AI agents together. Your contributions make the future of agent observability possible.

Expand All @@ -8,15 +8,15 @@ Search existing issues and pull requests to avoid duplicating efforts.

## How to Contribute

**Ideas**: Join issue discussions or start new ones. Your voice shapes AOS direction.
**Ideas**: Join issue discussions or start new ones. Your voice shapes ACS direction.

**Writing**: Expand documentation with your expertise. Clear explanations help everyone.

**Copy Editing**: Fix typos, clarify language, improve quality. Every word matters. Follow our [styling guide](./STYLE.md).

**Code**: Implement specifications, build tools, create examples.

**Standards**: Help Improve AOS, extend CycloneDX, SPDX, SWID for agent components.
**Standards**: Help Improve ACS, extend CycloneDX, SPDX, SWID for agent components.

## Development Process

Expand All @@ -39,7 +39,7 @@ All submissions require review via GitHub pull requests. Consult [GitHub Help](h
## What We Need

**High Priority:**
Look for unassigned [Open Issues](https://github.com/OWASP/www-project-agent-observability-standard/issues).
Look for unassigned [Open Issues](https://github.com/Agent-Control-Standard/ACS/issues).

**Always Welcome:**
- Documentation improvements
Expand Down Expand Up @@ -76,7 +76,7 @@ This guide is based on [github-contributing](https://raw.githubusercontent.com/s

## Community

- **[GitHub Discussions](https://github.com/OWASP/www-project-agent-observability-standard/discussions)**: Ask questions, share ideas
- **[Issues](https://github.com/OWASP/www-project-agent-observability-standard/issues)**: Report bugs, request features
- **[GitHub Discussions](https://github.com/Agent-Control-Standard/ACS/discussions)**: Ask questions, share ideas
- **[Issues](https://github.com/Agent-Control-Standard/ACS/issues)**: Report bugs, request features

We're building the future of AI agent observability. Join us.
34 changes: 17 additions & 17 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Agent Observability Standard
# Agent Control Standard

[![Apache License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](./LICENSE.txt)
[![MIT License](https://img.shields.io/badge/License-MIT-blue.svg)](./LICENSE.txt)

![AOS Banner](docs/assets/banner.png)
![ACS Banner](docs/assets/banner.png)

**Making AI agents trustworthy by standardizing observability.**

Expand All @@ -20,48 +20,48 @@ For agents to become trustworthy they must be **inspectable, traceable and instr
### Key Components

The standard covers the following aspects
1. AOS that defines the interaction between the Observed Agent and the Guardian Agent
2. Observability requirements and implementations for tracing all AOS events using OpenTelemetry and OCSF
1. ACS that defines the interaction between the Observed Agent and the Guardian Agent
2. Observability requirements and implementations for tracing all ACS events using OpenTelemetry and OCSF
3. Agent BOM (AgBOM) requirements and implementations for exposing dynamic Agent's bill-of-material via CoycloneDX, SWID and SPDX

## Getting Started

- 📚 **Explore the Documentation:** Visit the [Documentation Site](https://aos.owasp.org) for a complete overview, the full specification, tutorials, and guides.
- 📝 **View the Specification:** [Specification](https://github.com/OWASP/www-project-agent-observability-standard/tree/main/specification)
- 📚 **Explore the Documentation:** Visit the [Documentation Site](https://agentcontrolstandard.org) for a complete overview, the full specification, tutorials, and guides.
- 📝 **View the Specification:** [Specification](https://github.com/Agent-Control-Standard/ACS/tree/main/specification)

## Contributing

We welcome community contributions to enhance and evolve AOS!
We welcome community contributions to enhance and evolve ACS!

- **Questions & Discussions:** Join our [GitHub Discussions](do we have github enterprise?).
- **Issues & Feedback:** Report issues or suggest improvements via [GitHub Issues](https://github.com/OWASP/www-project-agent-observability-standard/issues).
- **Issues & Feedback:** Report issues or suggest improvements via [GitHub Issues](https://github.com/Agent-Control-Standard/ACS/issues).
- **Contribution Guide:** See our [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to contribute.

## What's next

#### v0.1 (Public Preview)
- Overall documentation and requirements
- AOS definitions and schema
- ACS definitions and schema
- Observability definitions for for OpenTelemetry and OCSF
- AgBOM requirements

#### v1
- Implementation of Agent instrumentation
- Implementation of Guardian Agent sample app with
- AOS Support
- AOS to OpenTelemetry mapper
- AOS to OCSF mapper
- FastMCP client instrumentation for AOS
- A2A client instrumentation for AOS
- ACS Support
- ACS to OpenTelemetry mapper
- ACS to OCSF mapper
- FastMCP client instrumentation for ACS
- A2A client instrumentation for ACS

#### v2
- Requirements for CycloneDX, SPDX, SWID
- Implementation of AOS to AgBOM mappers for CycloneDX, SPDX, SWID
- Implementation of ACS to AgBOM mappers for CycloneDX, SPDX, SWID

#### v3
- Extending A2A and MCP to support deny and modify operations
- Implementation of Agent with deny and modify support

## About

The AOS is an open-source project under the [Apache License 2.0](LICENSE), and is open to contributions from the community.
The ACS is an open-source project under the [MIT License](LICENSE.txt), and is open to contributions from the community.
4 changes: 2 additions & 2 deletions STYLE.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# AOS Editorial Style Guide
# ACS Editorial Style Guide

## Core Philosophy

Expand All @@ -20,7 +20,7 @@

### Language Choices
- Active voice dominates: "Agents expose events" not "Events are exposed by agents"
- Present tense when possible: "AOS provides" not "AOS will provide"
- Present tense when possible: "ACS provides" not "ACS will provide"
- Technical terms get defined once, then used freely

## Structure Guidelines
Expand Down
2 changes: 1 addition & 1 deletion docs/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -53,5 +53,5 @@ Early standardization provides a unique opportunity to build trustworthiness int

## Read Next

- [AOS](./aos.md)
- [ACS](./acs.md)
- [Core Concepts](./topics/core_concepts.md)
14 changes: 7 additions & 7 deletions docs/about.md
Original file line number Diff line number Diff line change
@@ -1,16 +1,16 @@
# About AOS
# About ACS

Agent Observability Standard (AOS) creates industry-wide transparency for AI agents.
Agent Control Standard (ACS) creates industry-wide transparency for AI agents.

## Mission

Transform AI agents from black boxes into trustworthy systems through standardized observability.

Enterprises need to see what agents do, understand why they act, and control their behavior. AOS provides the specifications and protocols to make this possible.
Enterprises need to see what agents do, understand why they act, and control their behavior. ACS provides the specifications and protocols to make this possible.

## What We're Building

**Instrumentation Standard**: AOS standard for agent instrumentation.
**Instrumentation Standard**: ACS standard for agent instrumentation.

**Standards Extensions**: Enhance CycloneDX, SPDX, SWID for AI agent components. Extend OCSF and OpenTelemetry with agent-specific schemas.

Expand All @@ -22,10 +22,10 @@ Enterprises need to see what agents do, understand why they act, and control the

## Join the Mission

AOS succeeds when the entire AI agent ecosystem adopts these standards. We're building this together.
ACS succeeds when the entire AI agent ecosystem adopts these standards. We're building this together.

- **Contribute**: Help shape the specifications
- **Implement**: Build AOS support in your agent platform
- **Implement**: Build ACS support in your agent platform
- **Advocate**: Spread the word about trustworthy agents

Contact us at [aos@zenity.io](mailto:aos@zenity.io).
Contact us at [acs@zenity.io](mailto:acs@zenity.io).
Loading
Loading