recommended
▱
Local (Docker)
Run everything on your machine.
- ✓ Full control, no external deps
- ✓ Data stays local
- ✓ Works offline
AutoMem
Persistent memory for every agent you use.
Open-source memory layer your agents and MCP tools can read, write, and reason over-across sessions and systems.
Claude, Cursor, Copilot, Codex, ChatGPT, and remote agents connect through MCP and Streamable HTTP.
$ automem install
curl -fsSL https://automem.ai/install.sh | sh
✓ detect environment ok
✓ choose local or cloud ok
✓ provision AutoMem ok
✓ wire MCP clients ok
macOS, Linux, and Windows (WSL2)
AGENT CLIENTS
⌬
Codex
AI
Claude Code
◈
Cursor
◌
ChatGPT
MCP
Model Context Protocol
AutoMem
Persistent Memory Layer
⌘
FalkorDB
Graph Storage
◈
Qdrant
Vector Store
Graph for relationships. Vector for meaning.
Why agent memory
From forgetful to brilliant.
Out of the box, every agent starts each session from zero — re-asking your stack, your conventions, the decision you settled yesterday. AutoMem is the memory layer that fixes that. It captures what matters as you work and recalls it the moment it's relevant, so your tools stop forgetting and start compounding.
ChatABC Pro
Standard
Built on research. Designed for recall.
AutoMem combines a knowledge graph and vector search so agents can recall both facts and their context.
⌘
Graph (FalkorDB) captures entities, relationships, and time.
✣
Vector (Qdrant) captures meaning, similarity, and intent.
# Example: hybrid recall
MATCH (p:Project)-[:USES]->(t:Tool)
WHERE p.name = 'AutoMem'
RETURN p, t
ORDER BY ts DESC
LIMIT 20;
# + vector search for semantic matches
SEARCH "install script errors WSL" LIMIT 20;The result: fewer repeats, more relevant answers, and memory that compounds over time.
Read the research overview →How it works
Dreams while you dream.
AutoMem runs quietly in the background, consolidating new memories into a retrieval graph. It clusters related ideas, strengthens the connections you return to, lets noise decay, and enriches recall — so the memory you get back tomorrow is sharper than the one you stored today.
MEMORY CORE AutoMem
Retrieval Graph
Ideas
Research
Habits
Code
recall.service
| ingest → normalize → link · 48ms
Works where agents already run
| Client / Platform | AutoMem MCP | macOS | Linux | Windows (WSL2) | Docker | Kubernetes |
|---|---|---|---|---|---|---|
| Codex (CLI) | MCP | ✓ | ✓ | ✓ | ✓ | ✓ |
| Claude Code | MCP | ✓ | ✓ | ✓ | ✓ | ✓ |
| Cursor | MCP | ✓ | ✓ | ✓ | ✓ | ✓ |
| ChatGPT (Code Interpreter) | MCP | ✓ | ✓ | ✓ | ✓ | ✓ |
| Custom MCP Clients | MCP | ✓ | ✓ | ✓ | ✓ | ✓ |
If your client supports MCP, AutoMem works. See full compatibility guide →
Extended compatibility: Claude Desktop, Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, ChatGPT, Any MCP-compatible client.
Choose your setup
Deploy Once. Remember Everywhere.
▤
Railway
Managed cloud in minutes.
- ✓ One-command deploy
- ✓ Auto updates & backups
- ✓ Global availability
⬡
InstaPods
Self-hosted cloud in your infra.
- ✓ Your VPC, your data
- ✓ K8s native
- ✓ Enterprise ready
All options expose the same MCP endpoint, including the Existing Endpoint path. Self-hosted / Docker remains available for teams that want full control. Learn more in the install guide →
What the installer does
1
Detect environment
Identifies OS, Docker/K8s, and available resources.
2
Choose deployment
You pick Local, Railway, InstaPods, or Existing Endpoint.
3
Provision AutoMem
Pulls images, starts services, and runs health checks.
4
Wire MCP clients
Generates config and shows you how to connect your agents.