Shared memory for multi-agent AI systems.
Quick Start • How It Works • Benchmarks • Adapters • API Docs • Config
Store a fact from Claude Code on your laptop, recall it from an autonomous agent on your server, get a briefing from n8n — all through the same memory system. Born from a production setup where nothing existed that let multiple AI agents share memory across separate machines.
You run multiple AI agents — Claude Code for development, autonomous agents for tasks, n8n for automation. They each maintain their own context and forget everything between sessions. When one agent discovers something important, the others never learn about it.
Events are immutable history. Facts upsert by key — new facts supersede old ones. Statuses track current state. Decisions record choices and reasoning. Each type has its own lifecycle, decay rules, and mutation semantics.
Every memory lives in a single Postgres database: pgvector (HNSW) for semantic vector search and structured tables for queries, entities, and full-text BM25 search. Get both "find memories similar to X" and "give me all facts with key Y" from the same system — one container, no separate vector service.
Search runs two retrieval paths in parallel, fused with Reciprocal Rank Fusion:
- Vector search — Cosine similarity via pgvector (HNSW)
- Keyword search — BM25 via Postgres tsvector
Items found by both paths get boosted. 98.4% retrieval accuracy on LongMemEval.
- Cross-agent briefings — "What happened since I was last here?" returns updates from all other agents
- Credential scrubbing — API keys, JWTs, passwords automatically redacted before storage
- Entity extraction — Regex + alias cache at write time
- LLM consolidation — Periodic background process merges duplicates, flags contradictions, discovers connections
Evaluated on LongMemEval, the academic benchmark for long-term conversational memory:
| Score | |
|---|---|
| Retrieval accuracy (finding the right memories) | 98.4% |
| QA accuracy (GPT-4o answering from retrieved context) | 76.0% |
| Full-context GPT-4o (entire history in prompt, no retrieval) | 72.4% |
The benchmark uses cosine similarity only — none of the API's multi-path features (BM25, temporal boost) were used. Full methodology and per-category breakdown.
LongMemEval tests single-agent chat recall. Zengram is built for multi-agent coordination — features like cross-agent briefings, typed memory, entity extraction, and credential scrubbing aren't measured by this benchmark but are core to production use.
| Feature | Zengram | Mem0 | Letta | Zep | Hindsight |
|---|---|---|---|---|---|
| Cross-machine by design | Yes | Cloud only | No | Cloud only | No |
| Typed memory (event/fact/status/decision) | Yes | No | No | No | No |
| Multi-path search (vector+BM25) | Yes | Vector only | Vector only | Hybrid | Yes |
| Cross-agent corroboration | Yes | No | No | No | No |
| Session briefings | Yes | No | No | No | No |
| Credential scrubbing | Yes | No | No | No | No |
| Entity extraction + linking | Yes | Graph (Pro) | No | Yes | No |
| LLM consolidation | Yes | Inline | Self-managed | No | Reflect |
| Temporal validity | Yes | No | No | Yes | No |
| MCP server included | Yes | Community | No | No | Yes |
| Self-hostable (fully open) | Yes | Community ed. | Yes | Graphiti only | Yes |
git clone https://github.com/ZenSystemAI/zengram.git
cd zengram
cp .env.example .env
# Edit .env — set BRAIN_API_KEY and your embedding provider key
docker compose up -d
# Verify
curl http://localhost:8084/health
# Store your first memory
curl -X POST http://localhost:8084/memory \
-H "Content-Type: application/json" \
-H "X-Api-Key: YOUR_KEY" \
-d '{
"type": "fact",
"content": "The API uses port 8084 by default",
"source_agent": "my-agent",
"key": "api-default-port"
}'13 tools: brain_store, brain_search, brain_briefing, brain_query, brain_stats, brain_consolidate, brain_entities, brain_delete, brain_update, brain_export, brain_import, brain_reflect, brain_research.
{
"mcpServers": {
"zengram": {
"command": "node",
"args": ["/path/to/zengram/mcp-server/src/index.js"],
"env": {
"BRAIN_API_URL": "http://localhost:8084",
"BRAIN_API_KEY": "your-key"
}
}
}
}Or install via npm: npm install -g @zensystemai/zengram-mcp
Copy adapters/claude-code/sessionend/ to your project's .claude/skills/ to get the /sessionend ritual — structured session reflections stored directly to Zengram. Full guide.
- Bash:
./adapters/bash/brain.sh store --type fact --content "Server migrated" - Any HTTP client: Plain REST — full reference
| Doc | Description |
|---|---|
| API Reference | Every endpoint with request/response examples |
| Architecture | System design, data flows, component inventory |
| Configuration | All environment variables |
| Data Model | Memory types, decay, dedup, supersedes logic |
| MCP Tools | The 13 MCP tools agents use |
| Operations | Deployment, monitoring, failure modes |
| Benchmarks | Full LongMemEval methodology and results |
| Examples | curl demo, Python client, multi-agent scenario |
Recently shipped: agentic iterate-until-sufficient retrieval (brain_research) with grounded [mem:<id>] citations, pgvector migration (single-Postgres storage), multi-collection support, on-demand LLM reflection, temporal validity, multi-path RRF search (vector + BM25) — full changelog
Coming next: Automatic memory capture, hosted docs, LangChain/LlamaIndex integration
Contributions welcome! See CONTRIBUTING.md.
- OpenClaw Memory Toolkit — Long-term memory for OpenClaw agents, with an optional bridge back to Zengram.
MIT — see LICENSE.
Built by ZenSystem AI