Know Your Agent — An open standard for AI agent identity, compliance, and auditability
Project description
KYA — Know Your Agent
An open standard for AI agent identity, compliance, and auditability.
What is KYA?
KYA defines a machine-readable Agent Card — a JSON document that declares who an AI agent is, what it can do, and how it has been audited. Think of it as a passport for AI agents.
Why?
- The EU AI Act requires conformity assessments for high-risk AI systems
- Enterprise procurement questionnaires ask "has your AI been audited?"
- Agent frameworks (MCP, LangChain, CrewAI) have no standard identity format
- No one can answer "what does this agent actually do?" in a verifiable way
KYA fills that gap.
Quick Start
pip install kya-agent
# Generate a skeleton agent card
kya init --agent-id "your-org/your-agent" --name "My Agent"
# Validate an agent card
kya validate agent-card.kya.json
# Score completeness
kya score agent-card.kya.json
Agent Card Example
{
"kya_version": "0.1",
"agent_id": "luciferforge/mcp-security-audit",
"name": "MCP Security Audit",
"version": "0.2.0",
"purpose": "Scans MCP servers for security vulnerabilities...",
"agent_type": "tool",
"owner": {
"name": "LuciferForge",
"contact": "luciferforge@proton.me"
},
"capabilities": {
"declared": [
{"name": "mcp_server_connection", "risk_level": "medium", "scope": "Read-only enumeration"}
],
"denied": ["code_execution", "data_exfiltration"]
},
"security": {
"last_audit": {"date": "2026-03-04", "score": 92, "tool": "mcp-security-audit v0.2.0"},
"injection_tested": true
},
"compliance": {
"frameworks": ["NIST-AI-RMF", "OWASP-LLM-Top-10"],
"risk_classification": "minimal",
"human_oversight": "human-above-the-loop"
}
}
Part of the LuciferForge Agent Safety Suite
| Package | Purpose |
|---|---|
| kya | Agent identity and compliance standard |
| mcp-security-audit | Security scanning for MCP servers |
| ai-injection-guard | Prompt injection detection (22 patterns) |
| ai-decision-tracer | Agent decision audit trails |
| ai-cost-guard | LLM budget enforcement |
| agent-safety-mcp | MCP server wrapping all safety tools |
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file kya_agent-0.2.0.tar.gz.
File metadata
- Download URL: kya_agent-0.2.0.tar.gz
- Upload date:
- Size: 24.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dc2c65b2f7a0c1b9683f9ae2f6bf72c43310217da9ae765d7706f01f24237804
|
|
| MD5 |
6077091d4934c4c0a40c24de740d6f62
|
|
| BLAKE2b-256 |
733e47b2be8070e9b43559040ad5a9a095bd7666b588bf694867f800db635459
|
File details
Details for the file kya_agent-0.2.0-py3-none-any.whl.
File metadata
- Download URL: kya_agent-0.2.0-py3-none-any.whl
- Upload date:
- Size: 13.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
35fcebfe3702085fbec887756bd8a3598d001f7d84721e435bd712911b6c6914
|
|
| MD5 |
47ce3f2f435bbf7f8b0e691884bb8bd5
|
|
| BLAKE2b-256 |
1b40f55a63636b3b0407a4820699d932535cdebe9ce2a3c6fa1ebb60076fd4a3
|