Memento
Give your AI tools a persistent memory — so every session starts where the last one left off.
Agenten stärken
Der eigene Befehl des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
docker run -i --rm ghcr.io/scrypster/memento:0.1.0Claude Code hat keinen Installationslink für einen lokalen Befehl. Kopieren Sie den Befehl unten und führen Sie ihn in einem Terminal aus.
claude mcp add io.github.scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0In einem Terminal ausführen.
{ "mcpServers": { "io.github.scrypster-memento": { "command": "docker", "args": [ "run", "-i", "--rm", "ghcr.io/scrypster/memento:0.1.0" ] } }}claude_desktop_config.json
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenYour AI starts fresh every session. Memento fixes that.
It runs on your machine, connects to any MCP-compatible AI tool, and builds a persistent knowledge graph from your conversations — entities, relationships, decisions, and context that survive every session restart.
No cloud. No API keys required. No subscriptions. Your data stays on your machine.
Prerequisites: Docker — or — Go 1.23+ + Node.js 18+ + Ollama
git clone https://github.com/scrypster/memento.git
cd memento
./launch.sh
The script detects your environment, runs preflight checks, builds everything, and prints the exact command to connect your AI tool at the end. First run downloads Ollama models (~5 GB). After that, starts in seconds.
Once connected, try this in Claude:
"We're using PostgreSQL — chose it for pgvector support."
Close the tab. Open a new session. Ask:
"What database are we using?"
Your AI already knows. No re-explaining. No context window tricks.
Close the tab. Open a new session.
You: "What database are we using?"
→ Your AI already knows: "PostgreSQL — you chose it for pgvector support."
No re-explaining. No context window tricks. It just remembers.
Behind the scenes, Memento built this automatically:
Every entity gets wired into a knowledge graph — people, tools, projects, decisions — with confidence scores and timestamps.
Open http://localhost:6363/integrations — the web UI generates configs, download buttons, and connection testing for every client:
The integrations page generates ready-to-paste configs with your actual binary paths and data directories. It also has connection testing, troubleshooting, and per-project workspace scoping.
The MCP connection makes tools available, but Claude won't use them automatically. Add this to ~/.claude/CLAUDE.md to make Claude store decisions and recall context without being asked:
## Memento MCP — Persistent Memory
The `memento` MCP server provides persistent cross-session memory. Use these tools proactively — don't wait to be asked.
**Store** (`store_memory`) when the user:
- States a preference or working style ("I prefer X", "always use Y format")
- Makes an architectural or technical decision
- Establishes project context that should survive session restarts
- Explicitly says "remember this" or similar
**Recall** (`recall_memory` or `find_related`) when:
- Starting a session for a known project — query for relevant context before diving in
- About to make a recommendation — check for existing preferences first
- The user asks about past decisions, choices, or "what did we decide about X"
- Something seems like it may have been discussed in a prior session
**Don't store:** transient debug output, in-progress exploration, or anything session-specific that won't matter next time.
Memories are searchable immediately after storing. Enrichment (entity/relationship extraction) runs asynchronously via local Ollama.
The web UI at Integrations → Claude Code → Make it proactive generates a version with your specific paths and connection settings, plus a download button.
See the full integration guides: Claude Code | Claude Desktop | Cursor & Windsurf | OpenClaw
Point everyone's AI tools at the same Memento instance and your team's decisions, conventions, and context become shared knowledge — queryable by anyone, attributable to anyone.
Every memory is tagged with who stored it. Memento auto-detects this from your git config, or you can set it explicitly:
export MEMENTO_USER=alice # or set in your shell profile
Or in your MCP config:
"env": { "MEMENTO_USER": "alice" }
Once set, you can ask:
What did Bob decide about the auth service this week?
recall_memory(created_by="bob", created_after="2024-01-14T00:00:00Z")
Setup: Each teammate runs Memento pointing at the same PostgreSQL database. Personal context stays personal (use a separate personal connection). Shared architectural decisions, conventions, and project context go into the shared connection.
See the team setup guide for full PostgreSQL configuration.
Once connected, your AI has 20 tools it can call — no prompting required:
Store returns in <10ms. Enrichment — entity extraction, relationship mapping, embedding generation — runs asynchronously. Your AI is never blocked.
People, projects, tools, organizations, languages, APIs — extracted automatically from your AI conversations. No tagging required.
Your AI knows who works_on what, which tools depend_on which services, and what the current state of each decision is — with confidence scores and timestamps.
Live enrichment queue, entity browser, relationship explorer, and graph visualizer — all in the web UI.
Mem0 requires cloud API keys and a paid plan for production use. Memento runs entirely on your machine with Ollama — no API keys, no cloud, no per-memory pricing. Memento also ships a full web UI with graph visualization, entity browser, and one-click integration setup. Mem0 has no web interface.
Zep requires Neo4j or FalkorDB for its knowledge graph. Memento uses SQLite (zero deps) or PostgreSQL — no graph database to manage. Zep's open-source version is limited; the full feature set requires Zep Cloud.
Built-in memory is a flat list of facts with no relationships, no search, no graph, and no way to export or control your data. Memento gives you a structured knowledge graph you own, with hybrid search and full lifecycle management.
Memento captures context automatically as you work — no manual effort. It builds relationships between concepts instead of isolated pages, and it's designed to be queried by LLMs, not just humans.
┌─────────────────────────────────────────────────────┐
│ Your AI tool (Cursor / Claude Code / Windsurf / …) │
└─────────────────────────┬───────────────────────────┘
│ MCP (JSON-RPC 2.0 over stdio)
┌─────────────────────────▼───────────────────────────┐
│ MCP Server │
│ store · recall · find_related · contradictions… │
└─────────────────────────┬───────────────────────────┘
│
┌─────────────────────────▼───────────────────────────┐
│ Memory Engine │
│ ┌──────────────────────────────────────────────┐ │
│ │ Enrichment Pipeline │ │
│ │ entity extraction → relationship mapping │ │
│ │ → semantic embeddings → contradiction check │ │
│ └──────────────────────────────────────────────┘ │
└──────────────────┬──────────────────────────────────┘
│
┌───────────┴───────────┐
│ │
┌──────▼──────┐ ┌────────▼────────┐
│ SQLite │ │ PostgreSQL │
│ FTS5 index │ │ + pgvector │
│ (default) │ │ (scale-out) │
└─────────────┘ └─────────────────┘
Runs entirely offline
~/.memento/memento.dbHybrid search
Knowledge graph
Memory lifecycle
planning → active → paused | blocked | completed | cancelled → archivedProduction-ready backends
Multi-connection isolation
Web UI
Switch providers per connection — different projects can use different LLMs.
docker compose --profile postgres up -d
MEMENTO_STORAGE_ENGINE=postgres
MEMENTO_DATABASE_URL=postgres://memento:memento_dev_password@localhost:5433/memento
memento/
├── cmd/
│ ├── memento-mcp/ # MCP server binary — connect this to your AI client
│ ├── memento-web/ # Web dashboard — entity browser, graph explorer, settings
│ └── memento-setup/ # Interactive setup wizard
├── internal/
│ ├── api/mcp/ # MCP JSON-RPC server — 20 tool handlers
│ ├── engine/ # Memory engine, enrichment pipeline, async workers
│ ├── llm/ # Ollama, OpenAI, Anthropic + circuit breaker
│ └── storage/
│ ├── sqlite/ # SQLite with FTS5 and hybrid vector search
│ └── postgres/ # PostgreSQL with pgvector and ivfflat index
├── web/
│ ├── handlers/ # HTMX handlers
│ ├── templates/ # Dashboard, graph, entities, settings, integrations
│ └── static/templates/ # MCP config snippets generated per client
├── docs/
│ └── integrations/ # Per-client integration guides
├── migrations/ # SQL schema migrations
└── docker-compose.yml
Issues and PRs welcome. Open an issue before starting significant work.
go test ./...
go build -o memento-mcp ./cmd/memento-mcp/
go build -o memento-web ./cmd/memento-web/
go build -o memento-setup ./cmd/memento-setup/
MIT — see LICENSE.
MJ Bonanno — software architect and founder of Scrypster.
Remember everything. Forget nothing. Unlike Leonard Shelby, your context is here to stay — searchable, versioned, and backed by a knowledge graph that never fades.
Persistent memory for AI tools. Local-first knowledge graph with hybrid search.
{ "mcpServers": { "io.github.scrypster-memento": { "command": "docker", "args": [ "run", "-i", "--rm", "ghcr.io/scrypster/memento:0.1.0" ] } }}Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Memento läuft lokal über stdio.
Zuletzt geprüft: 2026-11-10. Persistent memory for AI tools. Local-first knowledge graph with hybrid search.