Zengram
Active·★ 40·MIT·Updated 2026-04-12
★ Trending★ Multi-Agent★ Memory & Context
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
Zengram is a shared memory system for multi-agent AI systems, enabling agents to store and retrieve memories across machines. It features typed memory, dual storage (Qdrant + SQLite/Postgres), multi-path search, and cross-agent capabilities like briefings and corroboration. Self-hosted, open-source, with MCP server and SDKs.
#claude#claude-ai#claude-code#cursor#deduplication#embedded#longmemeval#mcp
01
Features
01Typed memory: events, facts, statuses, decisions
02Dual storage with semantic and structured search
03Multi-path search (vector, BM25, entity graph) with RRF fusion
04Cross-agent capabilities: briefings, corroboration, credential scrubbing
05Self-hosted, open-source, with MCP server and SDKs
02
Compatibility
Docker
Docker
Verified via docs
Node.js
Node 20+
Verified via docs
MCP
MCP
Verified via docs
Python
Python SDK
Verified via docs
REST API
REST API
Verified via docs
03
Quick start
1
$ git clone https://github.com/ZenSystemAI/zengram.git
2
$ cd zengram
3
$ cp .env.example .env
4
$ docker compose up -d
04
Use cases
↳Cross-agent memory sharing across different machines
↳Session reflection and context retrieval for agents
↳Logging memories from automation tools (e.g., n8n) for AI agents
05
Alternatives
letta★ 23.0k
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
DesktopCommanderMCP★ 6.1k
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
Auto-claude-code-research-in-sleep★ 11.0k
ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
openagent★ 5.1k
⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-agent) management platform with admin UI, user management and Single-Sign-On⚡️, supports ChatGPT, Claude, Llama, Ollama, HuggingFace, etc., chat bot demo: https://ai.casibase.com, admin UI demo: https://ai-admin.casibase.com
Related searches
Comments
Log in to leave a comment
- Phoenix ChenMay 26, 2026
Good for distributed agent setups where context needs to travel with the task.
- BBlake PatelApr 26, 2026
Cross-system agent memory that actually persists across machines and sessions.
- KKai KimApr 22, 2026
Reduces re-derivation overhead when agents pick up tasks mid-workflow.
- LLane DavisMar 13, 2026
Multi-agent coordination through shared memory is the right design.