Open Source · Apache 2.0

AI That Never Forgets —
Memory Infrastructure for Agents

Index your markdown notes, documents, and code into a searchable knowledge base for any AI agent. STM + LTM architecture preserves memory across sessions and shares knowledge between agents.

$ uv tool install memtomem
84MCP Tools
10Compression
6+Runtimes
0GPU Required
Why Do Agents Forget?
Tool integration (MCP), safety (Guardrails), and observability (Langfuse) are mature — but the memory layer still has no standard.
1

No Memory Between Sessions

All context is lost when a session ends. Architecture decisions, coding patterns, and debugging history must be re-explained every time.

2

Memory Silos Between Agents

Knowledge from Claude Code can't be carried over to Gemini CLI. Each agent is trapped in its own isolated memory silo.

3

Limitations of Existing Solutions

Current memory systems only work when agents explicitly search, are locked to specific runtimes, and offer only a single LTM layer.

memtomem Solves This
Applying the cognitive science working-memory / long-term memory model to agents. Short-term compression and long-term search as independent MCP servers.
S

Proactive Surfacing

Automatically inject relevant memories without agent request. 5-level relevance gating + feedback auto-tuning.

G

MCP Proxy Gateway

STM sits between agent and server as a transparent proxy. Memory injection into all MCP calls — no code changes.

C

Cross-Runtime Sync

Context Gateway auto-syncs agent definitions, skills, and commands across 6 runtimes.

10

10 Compression Strategies

Auto-selected by content type. Progressive delivery for zero information loss.

A

Multi-Agent Knowledge Sharing

Namespace isolation + sharing. Agent→Agent, Human→Agent — knowledge flows in all directions.

L

Fully Local

SQLite + ONNX. No GPU, no external services. 100% data sovereignty.

Two-Layer Architecture
STM proxy and LTM server connected via MCP, transparently providing memory to all agents.
AI Agents / Frameworks
Claude Code
Gemini CLI
Codex CLI
Cursor
LangGraph
↓ MCP
memtomem-stm (STM Proxy)
CLEAN → COMPRESS → SURFACE → INDEX
↕ Surfacing
↕ MCP
memtomem (LTM)
74 MCP Tools
Upstream MCP Servers
filesystem, GitHub, …
Supported Runtimes & Frameworks
MCP-native — works with any MCP-compatible client.
Claude Code
Cursor
Windsurf
Claude Desktop
Gemini CLI
Codex CLI
Antigravity
LangGraph
CrewAI
LangChain
Docs & Tutorials
From getting started to advanced usage.

Get Started Now

No GPU. No external services. One uv install is all you need.