Open source · MIT License · v0.1.1

Identity and trust
for AI agents

Every agent gets a cryptographic DID. Sign messages, verify sources, and discover agents by capability — with three lines of code.

View on GitHub See how it works
quickstart.py
from agentid import Agent

# One call — instant cryptographic identity
agent = Agent.create(
    name="research-agent",
    capabilities=["web-search", "summarization"],
    registry_url="https://api.agentid-protocol.com",
)

# → did:agentid:7sP3V2mNkQxRtYbLcDfHgJwAeUiMoZnXvBqKpTsWyE
print(agent.did)

# Sign outputs — anyone can verify
signed = agent.sign({"result": "task complete"})
Agent.verify_from_did(signed)  # → True
Ed25519
Cryptography
3
SDK languages
MIT
License
0
Central authority
The problem

Multi-agent systems have
no trust infrastructure

Every team building with AI agents hits the same three walls. AgentID tears them down.

🪪

Who is this agent?

No standard identity — every team hand-rolls their own auth. Agents can't prove who they are across systems.

🔍

Which agent can do X?

No discovery — agents are hardcoded or manually configured. Finding the right agent for a task is manual work.

🔏

Is this message genuine?

No signing — outputs can be spoofed or tampered with. There's no way to verify a message is authentic.

How it works

Permanent identity.
No central authority.

Every agent gets a DID derived from an Ed25519 keypair. No sign-up. Works offline. Cryptographically verifiable.

1

Generate a keypair

Ed25519 key generated locally. The DID is derived from the public key — no server involved.

2

Register in the public registry

Submit your DID, capabilities, and a cryptographic proof. The registry verifies ownership before accepting.

3

Sign and verify

Sign messages with your private key. Anyone verifies using only the DID — no shared secrets, no central login.

Live public registry
GET https://api.agentid-protocol.com/agents?capability=summarization
from agentid import Agent

# Create — generates keypair, registers
agent = Agent.create(
    name="analyst-v2",
    capabilities=["analysis", "reporting"],
    owner="team@company.com",
    registry_url="https://api.agentid-protocol.com",
)

# Discover agents by capability
agents = Agent.find(
    capability="analysis",
    registry_url="https://api.agentid-protocol.com",
)

# Sign a message
signed = agent.sign({"output": "Q3 revenue up 18%"})

# Verify from anywhere — no shared secret
valid = await Agent.verify_from_did(
    signed,
    registry_url="https://api.agentid-protocol.com",
)
print(valid)  # True
Integrations

Works with frameworks
you already use

Drop-in identity for the leading AI agent frameworks. One install, full AgentID support.

🦜

LangChain

Callback handler, identity tools, and automatic signing for LangChain agents and chains.

pip install agentid-protocol
🤖

AutoGen

ConversableAgent mixin with built-in discovery and verification for multi-agent conversations.

pip install agentid-protocol

CrewAI

Agent wrapper with AgentID tools for crew-to-crew trust and capability-based discovery.

pip install agentid-protocol
📦

TypeScript / Node

Full-featured SDK for TypeScript and Node.js projects. Identical API to the Python SDK.

npm install @vikhulus/agentid-protocol
Pricing

Start free.
Scale when you're ready.

The protocol is open source and free forever. Pay for the hosted registry and enterprise features.

Free
$0/mo
For developers and open source projects.
  • 100 registered agents
  • Public registry
  • DID resolution
  • Capability search
  • Ed25519 signing & verification
Get started free
Enterprise
Custom
For regulated industries and large-scale deployments.
  • Unlimited agents
  • Verified identity badges
  • Enterprise KYC
  • Compliance reports
  • SLA & dedicated support
  • Everything in Pro
Contact us

Give every agent
a verified identity

Open source, cryptographically sound, and ready for production.