🦜 LangChain
Official integration with automatic metadata generation for LangChain agents. Supports ReAct, conversational, and LangGraph patterns.
AgentFacts
The Universal KYA Standard for Agentic AI. Like nutrition facts for food, AgentFacts delivers standardized transparency for AI agents.
Know Your Agent (KYA)
Identity verification for AI agents. Verify capabilities, ensure compliance, establish trust across organizational boundaries.
AgentFacts provides standardized metadata for AI agent discovery, verification, and governance. A foundational cybersecurity infrastructure from Universitas AI research.
Multi Agent System Research
What is AgentFacts?
Standardized transparency for agentic AI systems
Just as consumers need standardized information about food before purchase, organizations need standardized metadata about AI agents before deployment. AgentFacts provides the Know Your Agent (KYA) infrastructure necessary for confident enterprise adoption.
The specification supports cryptographic multi-authority verification, enabling systematic agent procurement, governance, and coordination across organizational boundaries. Model and framework agnostic—works with OpenAI, Anthropic, open source models, LangChain, CrewAI, AutoGen, and more.
AgentFacts is actively implemented at Universitas AI for digital twin creation and recognized by leading research institutions. Enterprise pilots underway in financial services, gaming, and Web3 organizations.
Model & framework agnostic. Compatible with your existing AI stack.
🚢 CrewAI
Multi-agent crew verification. Generate AgentFacts for individual agents or entire crews with automatic role-based metadata.
🤖 AutoGen
Microsoft AutoGen integration with support for conversable agents and group chats. Community-maintained with active development.
Model Context Protocol
MCP server for seamless integration with Claude Desktop and other MCP-compatible applications. Deploy AgentFacts verification at the protocol level.
Universal 10-Category Framework
Comprehensive metadata for AI agent verification
Ten comprehensive categories providing standardized metadata for agentic AI discovery, verification, and governance. Supports JSON and JSON-LD formats for maximum interoperability.
From core identity and baseline model transparency to compliance automation and supply chain provenance, the framework covers everything organizations need to deploy AI agents with confidence.
1. Core Identity
Unique identification, names, versions, TTL management
2. Baseline Model
Foundation model transparency and safety evaluations
3. Classification
Agent type, operational level, stakeholder context
4. Capabilities
Tool calling, domain expertise, data formats, APIs
5. Authentication
Time-limited access control with audit trails
6. Compliance
EU AI Act, NIST, GDPR, sector-specific standards
7. Performance
Latency, availability SLAs, accuracy scores
8. Supply Chain
SBOM integration, dependencies, infrastructure
9. Verification
Cryptographic signatures, trust policies
10. Extensibility
Custom domains, hooks, backward compatibility
Industry Applications
Real-world deployment across sectors
Digital Twins at Universitas AI
Financial Services
Gaming & Content
Web3 & Blockchain
Healthcare & Safety
AgentFacts emerged from Universitas AI's multi-agent systems research. Published in ArXiv cs.MA, the standard addresses the fundamental coordination challenge in agentic AI deployment.
Apache 2.0 Licensed
Open standard infrastructure for the agentic AI ecosystem
Getting Started
Three paths to AgentFacts implementation
1. Use the Generator
Create AgentFacts metadata through guided workflow. Input basic information and get validated JSON output immediately.
2. Agent Integration
Use official integrations for LangChain, CrewAI, AutoGen, or MCP. Generate metadata automatically with minimal code changes.
3. Read the Research
Full technical specification published in ArXiv cs.MA with comprehensive methodology documentation.