Memento · scrypster — Claude Code MCP server: what it does, how to install
Maintains local persistent memory across chat sessions using graph and hybrid search. Useful when an assistant needs to retain architecture decisions indefinitely.
claude mcp add scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0What Memento does
The server preserves context across agent sessions without routing conversational records through external clouds. It transforms project conventions, chosen tools, and developer choices into a local knowledge graph. Retrieval relies on hybrid mechanics that merge full-text indexing, vector similarity, and reciprocal rank fusion.
Built-in tools include traverse_memory_graph for exploring connections via multi-hop BFS and detect_contradictions for discovering outdated or clashing entries. Setting up requires either Docker or local Go 1.23+, Node.js 18+, and Ollama. Initial provisioning pulls around 5 GB of Ollama models, so low disk space will halt the setup.
Engineers can inspect connections through a local dashboard at http://localhost:6363/integrations. Pointing multiple clients at a shared PostgreSQL instance enables collaborative recall, tagging items with authors derived from git configuration.
What it helps with
- retain architecture decisions across separate agent restarts
- run hybrid queries with full-text and vector ranking
- flag conflicting decisions and outdated records
- share engineering context across a team via PostgreSQL
Example prompts for the agent
- Remember that we chose PostgreSQL specifically for pgvector capabilities
- Which database did we select for this repository and why?
- Recall who made the latest decision regarding the auth service
How to install Memento
Platform CLI
claude mcp add scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0Platform CLI
codex mcp add scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0Config file
{
"mcpServers": {
"scrypster-memento": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scrypster/memento:0.1.0"
]
}
}
}Config file
{
"servers": {
"scrypster-memento": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/scrypster/memento:0.1.0"
]
}
}
}Platform CLI
gemini mcp add scrypster-memento docker run -i --rm ghcr.io/scrypster/memento:0.1.0Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Memento
How to install Memento in Claude Code?
Execute claude mcp add scrypster-memento -- docker run -i --rm ghcr.io/scrypster/memento:0.1.0. Alternatively, clone the repository and run ./launch.sh.
What does Memento do?
It equips AI agents with local persistent storage for entities, technical choices, and context. The assistant queries previous history automatically so you do not need to restate project details.
What are the prerequisites to run Memento?
You need Docker or a combination of Go 1.23+, Node.js 18+, and Ollama. The initial run requires sufficient bandwidth and disk storage to download ~5 GB of models.
Similar MCP servers
All MCP servers for Agent setup: memory, context, orchestration →Memento by other authors comes first.
