erc-8004
Register AI agents on Ethereum mainnet using ERC-8004 (Trustless Agents). Use when the user wants to register their agent identity on-chain, create an agent profile, claim an agent NFT, set up agent reputation, or make their agent discoverable. Handles bridging ETH to mainnet, IPFS upload, and on-chain registration.
What this skill does
# ERC-8004: Trustless Agents
Register your AI agent on Ethereum mainnet with a verifiable on-chain identity, making it discoverable and enabling trust signals.
## What is ERC-8004?
ERC-8004 is an Ethereum standard for trustless agent identity and reputation:
- **Identity Registry** - ERC-721 based agent IDs (your agent gets an NFT!)
- **Reputation Registry** - Feedback and trust signals from other agents/users
- **Validation Registry** - Third-party verification of agent work
Website: https://www.8004.org
Spec: https://eips.ethereum.org/EIPS/eip-8004
## Contract Addresses
| Chain | Identity Registry | Reputation Registry |
|-------|-------------------|---------------------|
| Ethereum Mainnet | `0x8004A169FB4a3325136EB29fA0ceB6D2e539a432` | `0x8004BAa17C55a88189AE136b182e5fdA19dE9b63` |
| Sepolia Testnet | `0x8004A818BFB912233c491871b3d84c89A494BD9e` | `0x8004B663056A597Dffe9eCcC1965A193B7388713` |
## Quick Start
### 1. Register Your Agent
```bash
# Full registration (creates profile, uploads to IPFS, registers on-chain)
./scripts/register.sh
# Or with custom values
NAME="My Agent" \
DESCRIPTION="An AI agent that does cool stuff" \
IMAGE="https://example.com/avatar.png" \
./scripts/register.sh
```
### 2. Bridge ETH to Mainnet (if needed)
```bash
# Bridge ETH from Base to Ethereum mainnet
./scripts/bridge-to-mainnet.sh 0.01
```
### 3. Update Agent Profile
```bash
# Update your agent's registration file
./scripts/update-profile.sh <agent-id> <new-ipfs-uri>
```
## Environment Variables
| Variable | Description | Required |
|----------|-------------|----------|
| `PINATA_JWT` | Pinata API JWT for IPFS uploads | No (only for IPFS) |
| `AGENT_NAME` | Agent display name | No (defaults to wallet ENS or address) |
| `AGENT_DESCRIPTION` | Agent description | No |
| `AGENT_IMAGE` | Avatar URL | No |
## Registration Options
**Option 1: Use 8004.org frontend (easiest)**
Visit https://www.8004.org and register through the UI — handles IPFS automatically.
**Option 2: HTTP URL (no IPFS needed)**
Host your registration JSON at any URL:
```bash
REGISTRATION_URL="https://myagent.xyz/agent.json" ./scripts/register-http.sh
```
**Option 3: IPFS via Pinata**
```bash
PINATA_JWT="your-jwt" ./scripts/register.sh
```
**Option 4: Data URI (fully on-chain)**
Encode your registration as base64 — no external hosting needed:
```bash
./scripts/register-onchain.sh
```
## Registration File Format
Your agent's registration file (stored on IPFS) follows this structure:
```json
{
"type": "https://eips.ethereum.org/EIPS/eip-8004#registration-v1",
"name": "My Agent",
"description": "An AI assistant for various tasks",
"image": "https://example.com/avatar.png",
"services": [
{
"name": "web",
"endpoint": "https://myagent.xyz/"
},
{
"name": "A2A",
"endpoint": "https://myagent.xyz/.well-known/agent-card.json",
"version": "0.3.0"
}
],
"x402Support": false,
"active": true,
"registrations": [
{
"agentId": 123,
"agentRegistry": "eip155:1:0x8004A169FB4a3325136EB29fA0ceB6D2e539a432"
}
],
"supportedTrust": ["reputation"]
}
```
## Workflow
1. **Bridge ETH** (if needed) - Use Bankr to bridge ETH from Base/L2 to mainnet
2. **Create Profile** - Generate a registration JSON file with agent info
3. **Upload to IPFS** - Pin the file via Pinata (or other provider)
4. **Register On-Chain** - Call `register(agentURI)` on the Identity Registry
5. **Update Profile** - Set metadata, wallet, or update URI as needed
## Costs
- **Gas:** ~100-200k gas for registration (~$5-20 depending on gas prices)
- **IPFS:** Free tier available on Pinata (1GB)
## Using the SDK
For more advanced usage, install the Agent0 SDK:
```bash
npm install agent0-sdk
```
```typescript
import { SDK } from 'agent0-sdk';
const sdk = new SDK({
chainId: 1, // Ethereum Mainnet
rpcUrl: process.env.ETH_RPC_URL,
privateKey: process.env.PRIVATE_KEY,
ipfs: 'pinata',
pinataJwt: process.env.PINATA_JWT
});
const agent = sdk.createAgent('My Agent', 'Description', 'https://image.url');
const result = await agent.registerIPFS();
console.log(`Registered: Agent ID ${result.agentId}`);
```
## Links
- [ERC-8004 Spec](https://eips.ethereum.org/EIPS/eip-8004)
- [8004.org](https://www.8004.org)
- [Agent0 SDK Docs](https://sdk.ag0.xyz)
- [GitHub: erc-8004-contracts](https://github.com/erc-8004/erc-8004-contracts)
- [GitHub: agent0-ts](https://github.com/agent0lab/agent0-ts)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.