Summary
This is a persistent memory layer for Claude that optimizes for access patterns. It maintains a hot cache of frequently used memories that get auto-injected into context before each request (zero latency), backed by a semantic search layer for everything else. The system self-organizes through promotion and demotion: memories used 3+ times move into the hot tier, unused ones decay after 14 days. It isolates memories per git repository, builds a knowledge graph between related concepts, and can bootstrap from your project docs. Exposes tools for remember, recall, promote/demote, and link_memories operations. Ships with a dashboard at localhost:8765 and works with local SQLite and embeddings. Reach for this when you're tired of re-explaining your architecture every session and want Claude to learn what matters in your codebase.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
🧠 Memory MCP
Give your AI assistant a persistent second brain
Stop re-explaining your project every session.
Memory MCP learns what matters and keeps it ready — instant recall for the stuff you use most, semantic search for everything else.
The Problem
Every new chat starts from scratch. You explain your architecture again. You paste the same patterns again. Your context window bloats with repetition.
Other memory solutions help, but they still require tool calls for every lookup — adding latency and eating into Claude's thinking budget.
Memory MCP fixes this with a two-tier architecture:
- Hot cache (0ms) — Frequently-used knowledge auto-injected into context before Claude even starts thinking. No tool call needed.
- Cold storage (~50ms) — Everything else, searchable by meaning via semantic similarity.
The system learns what you use and promotes it automatically. Your most valuable knowledge becomes instantly available. No manual curation required.
Before & After
| 😤 Without Memory MCP | 🎯 With Memory MCP |
|---|---|
| "Let me explain our architecture again..." | Project facts persist and isolate per repo |
| Copy-paste the same patterns every session | Patterns auto-promoted to instant access |
| 500k+ token context windows | Hot cache keeps it lean (~20 items) |
| Tool call latency on every memory lookup | Hot cache: 0ms — already in context |
| Stale information lingers forever | Trust scoring demotes outdated facts |
| Flat list of disconnected facts | Knowledge graph connects related concepts |
Install
# Install package
uv tool install hot-memory-mcp # or: pip install hot-memory-mcp
# Add plugin (recommended)
claude plugins add michael-denyer/memory-mcp
The plugin gives you auto-configured hooks, slash commands, and the Memory Analyst agent. MLX is auto-detected on Apple Silicon.
Manual config (no plugin)
Add to ~/.claude.json:
{
"mcpServers": {
"memory": {
"command": "memory-mcp"
}
}
}
See Reference for full configuration options.
Restart Claude Code. The hot cache auto-populates from your project docs.
First run: Embedding model (~90MB) downloads automatically. Takes 30-60 seconds once.
How It Works
flowchart LR
subgraph LLM["Claude"]
REQ((Request))
end
subgraph Hot["HOT CACHE · 0ms"]
HC[Session context]
PM[(Promoted memories)]
end
subgraph Cold["COLD STORAGE · ~50ms"]
VS[(Vector search)]
KG[(Knowledge graph)]
end
REQ -->|"auto-injected"| HC
HC -.->|"draws from"| PM
REQ -->|"recall()"| VS
VS <-->|"related"| KG
The hot cache (~10 items) is injected into every request — it combines recent recalls, predicted next memories, and top promoted items. Promoted memories (~20 items) is the backing store of frequently-used memories. Memories used 3+ times auto-promote; unused ones demote after 14 days.
What Makes It Different
Most memory systems make you pay a tool-call tax on every lookup. Memory MCP's hot cache bypasses this entirely — your most-used knowledge is already in context when Claude starts thinking.
| Memory MCP | Generic Memory Servers | |
|---|---|---|
| Hot cache | Auto-injected at 0ms | Every lookup = tool call |
| Self-organizing | Learns and promotes automatically | Manual curation required |
| Project-aware | Auto-isolates by git repo | One big pile of memories |
| Knowledge graph | Multi-hop recall across concepts | Flat list of facts |
| Pattern mining | Learns from Claude's outputs | Not available |
| Trust scoring | Outdated info decays and sinks | All memories equal |
| Setup | One command, local SQLite | Often needs cloud setup |
The Engram Insight: Human memory doesn't search — frequently-used patterns are already there. That's what hot cache does for Claude.
Quick Reference
| Slash Command | Tool | Description |
|---|---|---|
/memory-mcp:remember | remember | Store a memory with semantic embedding |
/memory-mcp:recall | recall | Search memories by meaning |
/memory-mcp:hot-cache | promote / demote | Manage promoted memories |
/memory-mcp:stats | memory_stats | Show statistics |
/memory-mcp:bootstrap | bootstrap_project | Seed from project docs |
| — | link_memories | Knowledge graph connections |
See Reference for all 14 slash commands and full tool API.
Dashboard
memory-mcp-cli dashboard # Opens at http://localhost:8765
Browse memories, hot cache, mining candidates, sessions, and knowledge graph.
How to Use
Memory MCP is designed to run as three complementary components:
| Component | Purpose |
|---|---|
| Claude Code Plugin | Hooks, slash commands, and Memory Analyst agent for seamless integration |
| MCP Server | Core memory tools available to Claude via Model Context Protocol |
| Dashboard | Web UI to browse, manage, and debug your memory database |
The plugin is recommended for most users — it auto-configures the MCP server and adds productivity features. Run the dashboard alongside when you want visibility into what's being stored.
Documentation
| Document | Description |
|---|---|
| Reference | Full API, CLI, configuration, MCP resources |
| Troubleshooting | Common issues and solutions |
License
MIT
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Configuration
MEMORY_MCP_DB_PATHPath to SQLite database file
MEMORY_MCP_EMBEDDING_MODELEmbedding model to use (default: all-MiniLM-L6-v2)
Categories
Registryactive
Packagehot-memory-mcp
TransportSTDIO
UpdatedJan 24, 2026
