Auto-discovered marketplace from michael-denyer/memory-mcp
npx claudepluginhub michael-denyer/memory-mcpPersistent memory for Claude Code with hot cache instant recall and semantic search. Give your AI assistant a second brain.
michael-denyer
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.
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:
The system learns what you use and promotes it automatically. Your most valuable knowledge becomes instantly available. No manual curation required.
| 😤 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| Stale information lingers forever | Trust scoring demotes outdated facts |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 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.
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.
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.
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.