AI.news
AI+医疗机器人教育金融能源健康

AgentRecall — Persistent Memory for AI Agents

Open source memory SDK for AI agents

Your agents forget everything
between sessions.

AgentRecall gives your AI agents persistent, intelligent memory. Graph relationships, semantic search, and AI-powered processing — so every conversation builds on the last.

Real problems. Real memory.

See how agents with memory outperform agents that forget.

🎧

Your support agent forgets every customer

The problem

Customer writes in: "We discussed this last week." Your agent has no idea. It treats every conversation like the first. Customer has to repeat themselves. Again.

With AgentRecall

Every interaction is stored as a connected memory. When the customer returns, your agent pulls up their history, preferences, and open issues — instantly.

const history = await recall.search({ query: "recent issues with this customer", agentId: "support-agent", limit: 5 });

Three lines to persistent memory

Install the SDK, initialize with your API key, and start storing memories. That's it.

npm install agentrecall pip install agentrecall

import { AgentRecall } from "agentrecall"; const recall = new AgentRecall({ mode: "cloud", apiKey: process.env.AGENTRECALL_API_KEY }); await recall.store({ content: "User wants the dashboard redesigned with dark mode", agentId: "ui-agent" }); const memories = await recall.search({ query: "what UI changes did the user request?", agentId: "ui-agent" }); const connected = await recall.traverse(memories[0].id, { depth: 2, relationship: "relates_to" });

Open source. Self-hostable. No vendor lock-in.

You don't need our cloud to use AgentRecall. Run everything on your own infrastructure with full control.

Self-Hosted

Run AgentRecall on your own server. Full control, no costs, no limits. Your data never leaves your infrastructure.

  • MIT licensed — use for anything
  • No API key needed
  • Unlimited memories, unlimited agents
  • Works with Claude Desktop via MCP
  • Docker or bare metal

Cloud

Don't want to manage infrastructure? Use our hosted API. Same features, zero setup.

  • Get started in 2 minutes
  • No server to manage
  • Free tier: 1,000 memories
  • AI processing included
  • Pro: $9/mo for unlimited

Same SDK, same API, same features. The only difference is where your data lives.

Memory that thinks

AgentRecall isn't a key-value store with a fancy name. It's a memory system built for how AI agents actually need to remember.

🔗

Graph Memory

Neo4j-powered relationship graph between memories. Memories aren't just stored — they're connected. Query by traversal, find hidden connections across your agent's entire history.

const related = await recall.traverse(memoryId, { depth: 3, relationship: "relates_to", filter: { topic: "project_alpha" } });

🧠

AI Memory Processing

Qwen2.5-7B extracts entities, detects relationships, and auto-categorizes every memory. Your agent's knowledge base is enriched automatically — no manual tagging needed.

await recall.store({ content: "User prefers dark mode and React", agentId: "support-agent" });

🔍

Semantic Search

Vector embeddings plus full-text search. Find memories by meaning, not just keywords. Your agent understands context and retrieves what's truly relevant.

const results = await recall.search({ query: "what did we discuss about pricing?", agentId: "support-agent", limit: 5, threshold: 0.7 });

☁️

Cloud API

RESTful API with authentication, usage tracking, and multi-agent support. Deploy in minutes, scale to millions of memories. Built for production workloads.

const recall = new AgentRecall({ mode: "cloud", apiKey: process.env.AGENTRECALL_API_KEY }); await recall.store({ content: "Session notes from standup", metadata: { team: "engineering" } });

🤖

Multi-Agent Support

Each agent gets isolated memory with its own namespace. Cross-agent query when needed. Perfect for teams of specialized agents working together.

const salesAgent = recall.agent("sales"); const supportAgent = recall.agent("support"); const shared = await recall.search({ query: "customer onboarding status", agents: ["sales", "support"] });

🔑

Bring Your Own Key

Local mode uses your own Neo4j and models. Cloud mode hosted by us. Same SDK, same API. Switch between modes with a single config change.

const local = new AgentRecall({ mode: "local", neo4j: "bolt://localhost:7687", model: "qwen2.5-7b" }); const cloud = new AgentRecall({ mode: "cloud", apiKey: process.env.AGENTRECALL_API_KEY });

Works with your agent

One MCP server. Three platforms. Install once, remember everything.

🤖

Claude Code

For developers

Persistent memory for your coding sessions. Remember architectural decisions, debugging context, and code patterns across sessions.

🦞

OpenClaw

For personal assistants

Your personal AI assistant that actually knows you. User preferences, relationships, daily routines — remembered forever.

Hermes Agent

For power users

Plug-and-play memory for CLI power users. One config line, full graph memory, semantic search. No Neo4j setup needed.

Simple, transparent pricing

Start free. Scale when you're ready. No surprises.

Free

$0forever

  • 1,000 memories
  • Basic semantic search
  • Single agent
  • Community support
  • Local mode (BYOK)

Get started for free

Pro

$9/month

  • Unlimited memories
  • Graph memory (Neo4j)
  • AI memory processing
  • Smart semantic search
  • Multi-agent support
  • Cloud API access
  • Priority support

Create Pro Account