Home Projects Zengram ZenVox 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.

Zengram is the shared brain that connects them all.


Store, search, and share memories

A REST API sits between your agents and a triple-path retrieval layer. Agents store memories with type, importance, and source metadata. Search combines vector similarity, BM25 keyword matching, and entity graph traversal — fused with Reciprocal Rank Fusion. 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/Zengram.git
cd Zengram
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. Zengram 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.