ERC-8004 is a Draft EIP for discovering, choosing, and interacting with AI agents across organizational boundaries without pre-existing trust. It defines three on-chain registries deployed as per-chain singletons on any EVM chain.
Authors: Marco De Rossi (MetaMask), Davide Crapis (EF), Jordan Ellis (Google), Erik Reppel (Coinbase)
Full spec: references/spec.md
agent0-sdk)Three lightweight registries, each deployed as a UUPS-upgradeable singleton:
RegistryPurposeContractIdentityERC-721 NFTs for agent identities + registration filesIdentityRegistryUpgradeableReputationSigned fixed-point feedback signals + off-chain detail filesReputationRegistryUpgradeableValidationThird-party validator attestations (stake, zkML, TEE)ValidationRegistryUpgradeable
Agent identity = agentRegistry (string eip155:{chainId}:{contractAddress}) + agentId (ERC-721 tokenId).
Each agent's agentURI points to a JSON registration file (IPFS or HTTPS) advertising name, description, endpoints (MCP, A2A, ENS, DID, wallet), OASF skills/domains, trust models, and x402 support.
See: references/contracts.md for full contract interfaces and addresses.
bash
npm install agent0-sdk
RPC_URL, PRIVATE_KEY, and PINATA_JWT are declared in this skill's metadata.openclaw.envVars. Use throwaway/testnet keys for development; reach for a hardware wallet or scoped signer for any mainnet activity.
typescript
import { SDK } from 'agent0-sdk';
const sdk = new SDK({
chainId: 84532, // Base Sepolia
rpcUrl: process.env.RPC_URL,
privateKey: process.env.PRIVATE_KEY,
ipfs: 'pinata',
pinataJwt: process.env.PINATA_JWT,
});
const agent = sdk.createAgent(
'MyAgent',
'An AI agent that analyzes crypto markets',
'https://example.com/agent-image.png'
);
// Configure endpoints and capabilities
await agent.setMCP('https://mcp.example.com', '2025-06-18', true); // auto-fetches tools
await agent.setA2A('https://example.com/.well-known/agent-card.json', '0.3.0', true);
agent.setENS('myagent.eth');
agent.setActive(true);
agent.setX402Support(true);
agent.setTrust(true, false, false); // reputation only
// Add OASF taxonomy
agent.addSkill('natural_language_processing/natural_language_generation/summarization', true);
agent.addDomain('finance_and_business/investment_services', true);
// Register on-chain (mints NFT + uploads to IPFS).
// Sends a real transaction signed with PRIVATE_KEY - confirm chainId, signer, and balance before running.
const tx = await agent.registerIPFS();
const { result } = await tx.waitConfirmed();
console.log(`Registered: ${result.agentId}`); // e.g. "84532:42"
typescript
const sdk = new SDK({ chainId: 84532, rpcUrl: process.env.RPC_URL });
// Search by capabilities
const agents = await sdk.searchAgents({
hasMCP: true,
active: true,
x402support: true,
mcpTools: ['financial_analyzer'],
supportedTrust: ['reputation'],
});
// Get a specific agent
const agent = await sdk.getAgent('84532:42');
// Semantic search
const results = await sdk.searchAgents(
{ keyword: 'crypto market analysis' },
{ sort: ['semanticScore:desc'] }
);
typescript
// Prepare optional off-chain feedback file
const feedbackFile = await sdk.prepareFeedbackFile({
text: 'Accurate market analysis',
capability: 'tools',
name: 'financial_analyzer',
proofOfPayment: { txHash: '0x...', chainId: '8453', fromAddress: '0x...', toAddress: '0x...' },
});
// Submit feedback (value=85 out of 100). On-chain tx; same caveats as `registerIPFS()` above.
const tx = await sdk.giveFeedback('84532:42', 85, 'starred', '', '', feedbackFile);
await tx.waitConfirmed();
// Read reputation summary
const summary = await sdk.getReputationSummary('84532:42');
console.log(`Average: ${summary.averageValue}, Count: ${summary.count}`);
See: references/sdk-typescript.md for full SDK API reference.
Every agent's agentURI resolves to this JSON structure:
json
{
"type": "https://eips.ethereum.org/EIPS/eip-8004#registration-v1",
"name": "MyAgent",
"description": "What it does, pricing, interaction methods",
"image": "https://example.com/agent.png",
"services": [
{ "name": "MCP", "endpoint": "https://mcp.example.com", "version": "2025-06-18", "mcpTools": ["tool1"] },
{ "name": "A2A", "endpoint": "https://example.com/.well-known/agent-card.json", "version": "0.3.0" },
{ "name": "OASF", "endpoint": "https://github.com/agntcy/oasf/", "version": "v0.8.0",
"skills": ["natural_language_processing/summarization"],
"domains": ["finance_and_business/investment_services"] },
{ "name": "ENS", "endpoint": "myagent.eth", "version": "v1" },
{ "name": "agentWallet", "endpoint": "eip155:8453:0x..." }
],
"registrations": [
{ "agentId": 42, "agentRegistry": "eip155:84532:0x8004A818BFB912233c491871b3d84c89A494BD9e" }
],
"supportedTrust": ["reputation", "crypto-economic", "tee-attestation"],
"active": true,
"x402Support": true
}
The registrations field creates a bidirectional cryptographic link: the NFT points to this file, and this file points back to the NFT. This enables endpoint domain verification via /.well-known/agent-registration.json.
See: references/registration.md for best practices (Four Golden Rules) and complete field reference.
All registries deploy to deterministic vanity addresses via CREATE2 (SAFE Singleton Factory):
RegistryAddressIdentity0x8004A169FB4a3325136EB29fA0ceB6D2e539a432Reputation0x8004BAa17C55a88189AE136b182e5fdA19dE9b63Validation0x8004Cb1BF31DAf7788923b405b754f57acEB4272
RegistryAddressIdentity0x8004A818BFB912233c491871b3d84c89A494BD9eReputation0x8004B663056A597Dffe9eCcC1965A193B7388713Validation0x8004Cb1BF31DAf7788923b405b754f57acEB4272
Same proxy addresses on: Ethereum, Base, Arbitrum, Avalanche, Celo, Gnosis, Linea, Mantle, MegaETH, Optimism, Polygon, Scroll, Taiko, Monad, BSC + testnets.
Feedback uses signed fixed-point numbers: value (int128) + valueDecimals (uint8, 0-18).
tag1MeasuresExamplevaluevalueDecimalsstarredQuality 0-10087/100870reachableEndpoint up (binary)true10uptimeUptime %99.77%99772successRateSuccess %89%890responseTimeLatency ms560ms5600
Anti-Sybil: getSummary() requires a non-empty clientAddresses array (caller must supply trusted reviewer list). Self-feedback is rejected (agent owner/operators cannot submit feedback on their own agent).
See: references/reputation.md for full feedback system, off-chain file format, and aggregation details.
Open Agentic Schema Framework provides standardized skills (136) and domains (204) for agent classification.
Top-level skill categories: natural_language_processing, images_computer_vision, audio, analytical_skills, multi_modal, agent_orchestration, advanced_reasoning_planning, data_engineering, security_privacy, evaluation_monitoring, devops_mlops, governance_compliance, tool_interaction, retrieval_augmented_generation, tabular_text
Top-level domain categories: technology, finance_and_business, healthcare, legal, education, life_science, agriculture, energy, environmental_science, government, manufacturing, transportation, and more.
Use slash-separated paths: agent.addSkill('natural_language_processing/natural_language_generation/summarization', true).
TermMeaningagentRegistry``eip155:{chainId}:{contractAddress} - globally unique registry identifieragentIdERC-721 tokenId - numeric on-chain identifier (format in SDK: "chainId:tokenId")agentURIURI (IPFS/HTTPS) pointing to agent registration fileagentWalletReserved on-chain metadata key for verified payment address (EIP-712/ERC-1271)feedbackIndex1-indexed counter of feedback a clientAddress has given to an agentIdsupportedTrustArray: "reputation", "crypto-economic", "tee-attestation"``x402SupportBoolean flag for Coinbase x402 HTTP payment protocol supportOASFOpen Agentic Schema Framework - standardized agent skills/domains taxonomyMCPModel Context Protocol - tools, prompts, resources, completionsA2AAgent2Agent - authentication, skills via AgentCards, task orchestration
ReferenceContentspec.mdComplete ERC-8004 specification (EIP text)contracts.mdSmart contract interfaces, storage layout, deploymentsdk-typescript.mdAgent0 TypeScript SDK full APIregistration.mdRegistration file format, Four Golden Rules, domain verificationreputation.mdFeedback system, off-chain files, value encoding, aggregationsearch-discovery.mdAgent search, subgraph queries, multi-chain discoveryoasf-taxonomy.mdComplete OASF v0.8.0 taxonomy: all 136 skills and 204 domains with slugs