You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
**Making AI agents trustworthy by standardizing observability.**
8
8
@@ -20,48 +20,48 @@ For agents to become trustworthy they must be **inspectable, traceable and instr
20
20
### Key Components
21
21
22
22
The standard covers the following aspects
23
-
1.AOS that defines the interaction between the Observed Agent and the Guardian Agent
24
-
2. Observability requirements and implementations for tracing all AOS events using OpenTelemetry and OCSF
23
+
1.ACS that defines the interaction between the Observed Agent and the Guardian Agent
24
+
2. Observability requirements and implementations for tracing all ACS events using OpenTelemetry and OCSF
25
25
3. Agent BOM (AgBOM) requirements and implementations for exposing dynamic Agent's bill-of-material via CoycloneDX, SWID and SPDX
26
26
27
27
## Getting Started
28
28
29
-
- 📚 **Explore the Documentation:** Visit the [Documentation Site](https://aos.owasp.org) for a complete overview, the full specification, tutorials, and guides.
30
-
- 📝 **View the Specification:**[Specification](https://github.com/OWASP/www-project-agent-observability-standard/tree/main/specification)
29
+
- 📚 **Explore the Documentation:** Visit the [Documentation Site](https://agentcontrolstandard.org) for a complete overview, the full specification, tutorials, and guides.
30
+
- 📝 **View the Specification:**[Specification](https://github.com/Agent-Control-Standard/ACS/tree/main/specification)
31
31
32
32
## Contributing
33
33
34
-
We welcome community contributions to enhance and evolve AOS!
34
+
We welcome community contributions to enhance and evolve ACS!
35
35
36
36
-**Questions & Discussions:** Join our [GitHub Discussions](do we have github enterprise?).
37
-
-**Issues & Feedback:** Report issues or suggest improvements via [GitHub Issues](https://github.com/OWASP/www-project-agent-observability-standard/issues).
37
+
-**Issues & Feedback:** Report issues or suggest improvements via [GitHub Issues](https://github.com/Agent-Control-Standard/ACS/issues).
38
38
-**Contribution Guide:** See our [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to contribute.
39
39
40
40
## What's next
41
41
42
42
#### v0.1 (Public Preview)
43
43
- Overall documentation and requirements
44
-
-AOS definitions and schema
44
+
-ACS definitions and schema
45
45
- Observability definitions for for OpenTelemetry and OCSF
46
46
- AgBOM requirements
47
47
48
48
#### v1
49
49
- Implementation of Agent instrumentation
50
50
- Implementation of Guardian Agent sample app with
51
-
-AOS Support
52
-
-AOS to OpenTelemetry mapper
53
-
-AOS to OCSF mapper
54
-
- FastMCP client instrumentation for AOS
55
-
- A2A client instrumentation for AOS
51
+
-ACS Support
52
+
-ACS to OpenTelemetry mapper
53
+
-ACS to OCSF mapper
54
+
- FastMCP client instrumentation for ACS
55
+
- A2A client instrumentation for ACS
56
56
57
57
#### v2
58
58
- Requirements for CycloneDX, SPDX, SWID
59
-
- Implementation of AOS to AgBOM mappers for CycloneDX, SPDX, SWID
59
+
- Implementation of ACS to AgBOM mappers for CycloneDX, SPDX, SWID
60
60
61
61
#### v3
62
62
- Extending A2A and MCP to support deny and modify operations
63
63
- Implementation of Agent with deny and modify support
64
64
65
65
## About
66
66
67
-
The AOS is an open-source project under the [Apache License 2.0](LICENSE), and is open to contributions from the community.
67
+
The ACS is an open-source project under the [MIT License](LICENSE.txt), and is open to contributions from the community.
Agent Observability Standard (AOS) creates industry-wide transparency for AI agents.
3
+
Agent Control Standard (ACS) creates industry-wide transparency for AI agents.
4
4
5
5
## Mission
6
6
7
7
Transform AI agents from black boxes into trustworthy systems through standardized observability.
8
8
9
-
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.
9
+
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.
10
10
11
11
## What We're Building
12
12
13
-
**Instrumentation Standard**: AOS standard for agent instrumentation.
13
+
**Instrumentation Standard**: ACS standard for agent instrumentation.
14
14
15
15
**Standards Extensions**: Enhance CycloneDX, SPDX, SWID for AI agent components. Extend OCSF and OpenTelemetry with agent-specific schemas.
16
16
@@ -22,10 +22,10 @@ Enterprises need to see what agents do, understand why they act, and control the
22
22
23
23
## Join the Mission
24
24
25
-
AOS succeeds when the entire AI agent ecosystem adopts these standards. We're building this together.
25
+
ACS succeeds when the entire AI agent ecosystem adopts these standards. We're building this together.
26
26
27
27
-**Contribute**: Help shape the specifications
28
-
-**Implement**: Build AOS support in your agent platform
28
+
-**Implement**: Build ACS support in your agent platform
29
29
-**Advocate**: Spread the word about trustworthy agents
30
30
31
-
Contact us at [aos@zenity.io](mailto:aos@zenity.io).
31
+
Contact us at [acs@zenity.io](mailto:acs@zenity.io).
0 commit comments