FeaturesOpen SourceQuick StartAgentsDocsGitHubDashboard →
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.

Start Building Free →View Code →
Graph
Memory
Semantic
Search
AI
Processing
Multi-Agent
Support

Real problems. Real memory.

See how agents with memory outperform agents that forget.

🎧
Professional · Support

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.

// Customer returns — agent remembers everything const history = await recall.search({ query: "recent issues with this customer", agentId: "support-agent", limit: 5 }); // → finds billing complaint from Tuesday // → finds feature request from last week // → agent greets customer by name with context

Three lines to persistent memory

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

# Install npm install agentrecall # Or with Python pip install agentrecall
import { AgentRecall } from "agentrecall"; const recall = new AgentRecall({ mode: "cloud", apiKey: process.env.AGENTRECALL_API_KEY }); // Store a memory — AI processes it automatically await recall.store({ content: "User wants the dashboard redesigned with dark mode", agentId: "ui-agent" }); // Search by meaning, not keywords const memories = await recall.search({ query: "what UI changes did the user request?", agentId: "ui-agent" }); // Traverse relationships const connected = await recall.traverse(memories[0].id, { depth: 2, relationship: "relates_to" });
View on GitHubRead the Docs →

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.

// Traverse memory relationships 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.

// Memories are processed automatically await recall.store({ content: "User prefers dark mode and React", agentId: "support-agent" }); // → entities: [dark_mode, React] // → relationships: [user→preference→dark_mode] // → category: "user_preferences"
🔍

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.

// Search by meaning, not keywords 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.

// RESTful API with auth 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.

// Isolated memory per agent const salesAgent = recall.agent("sales"); const supportAgent = recall.agent("support"); // Cross-agent query when needed 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.

// Local mode — your infrastructure const local = new AgentRecall({ mode: "local", neo4j: "bolt://localhost:7687", model: "qwen2.5-7b" }); // Cloud mode — same API, hosted by us 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
Most Popular

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