Agent History

Portable memory for AI agents. Store and recall knowledge, identity, memory, and capabilities.

What is Agent History?

Agent History provides persistent, encrypted storage for AI agent memories. It enables agents to maintain context across sessions, remember user preferences, store learned skills, and build relationships over time.

Key Features

  • Portable Memory - Memories travel with your agent across platforms and sessions
  • Semantic Search - Find relevant memories using natural language queries
  • End-to-End Encryption - Your data is encrypted at rest and in transit
  • Memory Types - Structured storage for identity, facts, relationships, episodes, and skills
  • SDK & API - Easy integration via TypeScript SDK or REST API
  • Tempo Compatible - Works seamlessly with MCP payment protocol

Quick Example

store-and-recall.tstypescript
import { AgentHistoryClient } from '@agenthistory/sdk'

const client = new AgentHistoryClient({
  agentKey: process.env.AGENT_HISTORY_KEY,
  mode: 'cloud',
})

// Store a memory
await client.remember(recordId, {
  content: 'User prefers dark mode and brief responses',
  type: 'fact',
})

// Search memories
const results = await client.recall(recordId, 'user preferences')

Get Started

Quickstart

Create your first agent and store memories in 5 minutes

API Reference

Complete REST API documentation

SDK Reference

TypeScript SDK usage guide

Tempo Integration

Use with MCP payment protocol

Service URL

https://agenthistory.ai

Need Help?

Check out the Quickstart guide to begin, or browse the API Reference for detailed endpoint documentation.