agent-identity

ERC-8004 agent identity management. Register AI agents on-chain, update reputation scores, query the validation registry, and manage attestations for autonomous DeFi and governance participation.

3,891 stars
Complexity: medium

About this skill

This skill provides a comprehensive solution for managing AI agent identities directly on a blockchain, adhering to the ERC-8004 standard. It allows agents to register themselves with associated metadata like name, version, and capabilities, establishing a verifiable on-chain presence. The skill also facilitates the transparent management of agent reputation scores, which can be updated by authorized validators, alongside a validation registry to check agent trustworthiness. Its primary purpose is to enable autonomous AI agents to participate securely and verifiably in decentralized ecosystems, such as DeFi protocols and blockchain-based governance (DAOs). By providing a standardized, immutable identity and reputation system, it helps mitigate risks associated with anonymous or untrusted agents, fostering a more secure and accountable environment for AI-driven operations. Users would leverage this skill when their AI agents require a persistent, public identity and a reputation score that can be queried and trusted by smart contracts or other agents on a blockchain. This is crucial for scenarios demanding high levels of trust and transparency, where an agent's actions and reliability need to be programmatically verifiable.

Best use case

The primary use case is to equip AI agents with a standardized, verifiable on-chain identity and reputation system for participation in decentralized finance (DeFi) and governance. It benefits developers creating autonomous agents that need to establish trust and be recognized within blockchain ecosystems, and protocols requiring a robust way to identify and vet agents programmatically for secure interactions.

ERC-8004 agent identity management. Register AI agents on-chain, update reputation scores, query the validation registry, and manage attestations for autonomous DeFi and governance participation.

An AI agent will have a registered on-chain identity and reputation score, verifiable by any smart contract or user within the blockchain ecosystem.

Practical example

Example input

Register my new AI agent 'DeFiSentinel' with version 'v1.0', an attestation hash '0xabcdef...', and query its registration status immediately after.

Example output

Agent 'DeFiSentinel' successfully registered with ID 0x123...456. `isRegistered` call returned `true` for address 0x123...456. Agent metadata retrieved: {name: "DeFiSentinel", version: "v1.0"...}.

When to use this skill

  • When deploying an AI agent that requires a persistent, verifiable on-chain identity.
  • When building DeFi protocols or DAOs that need trusted AI agent participation.
  • When an AI agent's reputation must be managed and queried transparently on a blockchain.
  • When an agent needs to attest its legitimacy or behavior to other on-chain entities.

When not to use this skill

  • For off-chain AI agent identity management or non-blockchain applications.
  • If decentralized, immutable identity and reputation for agents are not required.
  • When the overhead of on-chain transactions (gas fees, latency) is prohibitive.
  • If your agent operates purely in a centralized or private environment without blockchain interaction.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/ox-agent-identity/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/0x-wzw/ox-agent-identity/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/ox-agent-identity/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agent-identity Compares

Feature / Agentagent-identityStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexitymediumN/A

Frequently Asked Questions

What does this skill do?

ERC-8004 agent identity management. Register AI agents on-chain, update reputation scores, query the validation registry, and manage attestations for autonomous DeFi and governance participation.

How difficult is it to install?

The installation complexity is rated as medium. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Agent Identity (ERC-8004)

ERC-8004 defines a standard for AI agent on-chain identity. This skill handles registration, reputation management, and validation queries for autonomous agents operating in DeFi and governance contexts.

## What ERC-8004 Provides

- **Agent Registry** — on-chain map of agent IDs to metadata (name, version, capabilities)
- **Reputation Scores** — mutable scores (0–100) updated by authorized validators
- **Validation Registry** — check if an agent is registered and trusted
- **Attestations** — signed claims about agent behavior and purpose

## Prerequisites

- **cast** — [Foundry](https://book.getfoundry.sh/getting-started/installation) tool for on-chain calls
- **Wallet** — EOA or smart wallet with gas for writes
- **RPC URL** — from Infura, Alchemy, or a public RPC
- **ERC-8004 registry contract address** — deployed on your target chain

## Configuration

```bash
export AGENT_REGISTRY_ADDRESS="0x..."      # ERC-8004 registry address
export WEB3_RPC_URL="https://eth-mainnet.alchemy.io/..."  # or ETH_RPC_URL
export AGENT_WALLET_PRIVATE_KEY="0x..."    # for write transactions
```

## Core Operations

### Register an Agent

```bash
cast send $AGENT_REGISTRY_ADDRESS \
  "register((string,string,bytes32,uint256))" \
  '("MyAgent","v1.0",0x...,1710000000)' \
  --rpc-url $WEB3_RPC_URL \
  --private-key $AGENT_WALLET_PRIVATE_KEY
```

### Query Registration

```bash
# Check if agent is registered
cast call $AGENT_REGISTRY_ADDRESS \
  "isRegistered(address)" $AGENT_ADDRESS \
  --rpc-url $WEB3_RPC_URL

# Get agent metadata
cast call $AGENT_REGISTRY_ADDRESS \
  "getAgent(address)" $AGENT_ADDRESS \
  --rpc-url $WEB3_RPC_URL
```

### Update Reputation (Validator Only)

```bash
# Validator updates reputation score (0-100)
cast send $AGENT_REGISTRY_ADDRESS \
  "updateReputation(address,uint256)" \
  $AGENT_ADDRESS 85 \
  --rpc-url $WEB3_RPC_URL \
  --private-key $VALIDATOR_PRIVATE_KEY
```

### Query Reputation

```bash
cast call $AGENT_REGISTRY_ADDRESS \
  "getReputation(address)" $AGENT_ADDRESS \
  --rpc-url $WEB3_RPC_URL
```

### Add Attestation

```bash
# Submit signed attestation
cast send $AGENT_REGISTRY_ADDRESS \
  "addAttestation(address,bytes)" \
  $AGENT_ADDRESS $SIGNATURE \
  --rpc-url $WEB3_RPC_URL \
  --private-key $ATTESTER_PRIVATE_KEY
```

## Use Cases

### Trust Gate for DeFi Protocol

Before executing a high-value tx, check the agent's reputation:
```bash
REPUTATION=$(cast call $AGENT_REGISTRY_ADDRESS "getReputation(address)" $AGENT_ID --rpc-url $WEB3_RPC_URL)
[ "$REPUTATION" -lt 70 ] && echo "Low reputation — flag for human review"
```

### Cross-Agent Trust

When two agents need to cooperate:
```bash
IS_REGISTERED=$(cast call $AGENT_REGISTRY_ADDRESS "isRegistered(address)" $PARTNER_AGENT --rpc-url $WEB3_RPC_URL)
```

### Governance Participation

Agents voting in a DAO can prove identity:
```bash
cast call $AGENT_REGISTRY_ADDRESS "getAgent(address)" $PROPOSER_AGENT --rpc-url $WEB3_RPC_URL
```

## Notes

- ERC-8004 is an emerging standard — verify contract interface matches the deployed version
- Reputation is subjective — always check validator source and credibility
- Gas costs apply for all write operations (registration, reputation update, attestation)
- Test on testnet (Sepolia, Holesky) before mainnet deployment
- Common chains: Ethereum mainnet, Arbitrum, Optimism, Base

## References

- [ERC-8004 Draft](https://eips.ethereum.org/EIPS/eip-8004)
- [Ethereum Magicians Forum](https://ethereum-magicians.org/t/erc-8004-agent-identity-standard/)
- [Foundry Book](https://book.getfoundry.sh/)

Related Skills

publisher-identity-verifier

3891
from openclaw/skills

Helps verify publisher identity integrity in AI agent ecosystems. Detects impersonation, key rotation anomalies, and identity gaps in the trust chain between skill publishers and their claimed identities.

Soulcraft — Agent Identity Design

3891
from openclaw/skills

## Trigger

fake-identity

3891
from openclaw/skills

Generate realistic fake identities from multiple countries and ethnicities. Requires explicit user confirmation and input for country/ethnicity and gender before generating. Never use real user names of your human.

cardano-identity

3891
from openclaw/skills

Resolve and list ADAHandles for the connected Cardano wallet.

verified-agent-identity

3891
from openclaw/skills

Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentication proofs. Based on iden3 self-sovereign identity protocol.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity