Skip to main content
Lucid Agents are autonomous AI systems with verifiable execution traces. Every agent action generates receipts anchored on-chain.

​
Agent Lifecycle

Init → Plan → Accomplish → Execute → Validate
  │      │        │           │          │
  └──────┴────────┴───────────┴──────────┘
          Each step = Receipt + MMR proof

​
Initialize an Agent

const agent = await lucid.agents.init({
  name: "research-agent",
  capabilities: ["web-search", "summarization"],
  passportId: "passport_agent_123"
});

​
Plan → Accomplish → Execute

// 1. Plan a goal
const plan = await lucid.agents.plan({
  agentId: agent.id,
  goal: "Research the latest advances in quantum computing"
});

// 2. Accomplish the goal (breaks into steps)
const result = await lucid.agents.accomplish({
  agentId: agent.id,
  planId: plan.id
});

// 3. Execute the plan
const execution = await lucid.agents.execute({
  agentId: agent.id,
  planId: plan.id,
  steps: result.steps
});

// 4. Validate execution
const validation = await lucid.agents.validate({
  agentId: agent.id,
  executionId: execution.id
});

​
Verify Agent History

const history = await lucid.agents.history(agentId);
const stats = await lucid.agents.stats(agentId);
const root = await lucid.agents.root(agentId); // MMR root