multi-agent-memory
Active·★ 40·MIT·Updated 2026-04-12
★ Trending★ Multi-Agent★ Memory & Context
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
Multi-Agent Memory is a cross-machine, cross-agent persistent memory system for AI agents. It provides a shared brain that works across machines, tools, and frameworks, allowing agents to store and recall facts, events, statuses, and decisions. Features include typed memory, entity extraction, LLM consolidation, credential scrubbing, and agent isolation.
#claude#cursor#deduplication#embedded#mcp#mcp-server#mcp-servers#memory
01
Features
01Typed memory with mutation semantics (event, fact, status, decision)
02Entity extraction and linking with fast and smart paths
03Credential scrubbing before storage
04Agent isolation and API gatekeeping
05Session briefings for catching up on changes
02
Compatibility
Node.js
Node 20+
Verified via docs
Docker
Docker Ready
Verified via docs
MCP
MCP Compatible
Verified via docs
Qdrant
Native Vector DB
Verified via docs
SQLite
Default Structured Store
Verified via docs
PostgreSQL
Production Structured Store
Verified via docs
03
Quick start
1
$ git clone https://github.com/ZenSystemAI/multi-agent-memory.git
2
$ cd multi-agent-memory
3
$ cp .env.example .env
4
$ docker compose up -d
04
Use cases
↳Sharing context between multiple AI agents (e.g., Claude Code, OpenClaw, n8n) across different machines
↳Persisting knowledge across sessions for autonomous agents
↳Centralized memory for multi-agent workflows and automation
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
FunASR★ 16.6k
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
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
- EElliot KimMay 14, 2026
Works well for long-running workflows that span multiple agent instances.
- SSutton RiveraMay 10, 2026
Shared memory layer for multi-agent systems that works across process boundaries.
- EEmerson WilsonApr 17, 2026
Agents can hand off tasks with full context — no cold-start overhead.
- SSam ThompsonApr 15, 2026
Simple API, the coordination logic lives in your agents, not the memory layer.