Home Projects Multi-Agent Memory OpenClaw Memory Toolkit View on GitHub

Your agents don't talk to each other

You don't run one AI agent — you run many. Claude Code on your laptop, an autonomous agent on a server, n8n workflows on another machine. Each one maintains its own context. When one discovers something important, the others never learn about it.

Multi-Agent Memory is the shared brain that connects them all.


Store, search, and share memories

A REST API sits between your agents and a dual storage layer. Agents store memories with type, importance, and source metadata. The system handles embeddings, credential scrubbing, deduplication, and decay automatically.

4 memory types, each with different behavior:

Type Purpose Decays? Example
event Something happened No "Deploy completed at 14:30"
fact Persistent knowledge Yes "Client prefers formal tone"
status Current state (supersedes previous) Yes "API rate limit: 100/min"
decision Choices made with reasoning No "Chose Postgres over MySQL for X"

How it all connects

Hover over any node to learn what it does. Data flows left to right — agents store and search memories through a central API backed by dual storage.

Agents
MCP Server
Claude Code, Cursor
OpenClaw
Drop-in skill
n8n
Workflow automation
Any HTTP Client
REST API / Bash CLI
Core
Memory API
Embeddings · Scrubbing · Decay
LLM Consolidation
Merge · Deduplicate · Score
event fact status decision
Storage
Qdrant
Vector search
Structured DB
SQLite / Postgres / Baserow

↑ Hover a node to see details


Up and running in 60 seconds

git clone https://github.com/ZenSystemAI/multi-agent-memory.git
cd multi-agent-memory
cp .env.example .env
# Edit .env with your API keys
docker compose up -d

That's it. Qdrant + the Memory API are running. Point your agents at localhost:8084.


Built in production

This isn't a weekend project. Multi-Agent Memory runs in production coordinating 10+ AI agents across 3 machines, powering client deliverables for a digital agency. It was built because nothing on the market handled cross-machine agent memory well.