Memento

scrypster/memento

Adds 20 MCP tools that give Claude persistent memory across sessions using a local knowledge graph. Store decisions, preferences, and context with `store_memory`, then retrieve them later with `recall_memory` or `find_related` (hybrid full-text and semantic search). Includes graph traversal for entity relationships, contradiction detection, memory versioning with `evolve_memory`, and project management primitives. Runs locally with PostgreSQL and Ollama for embeddings and entity extraction. Connect it to Claude Desktop, Cursor, Windsurf, or any MCP client. Point multiple team members at the same database for shared architectural memory. Good for long-running projects where you're tired of re-explaining decisions every session.

GitHub stars: 9
tools: 17
transport: STDIO
last updated: Feb 20, 2026

View on GitHub

Tools

17 tools

Public tool metadata for what this MCP can expose to an agent.

create_entitiesCreate multiple new entities in your Memento MCP knowledge graph memory system1 params

Create multiple new entities in your Memento MCP knowledge graph memory system

Parameters* required

entitiesarray

create_relationsCreate multiple new relations between entities in your Memento MCP knowledge graph memory. Relations should be in active voice1 params

Create multiple new relations between entities in your Memento MCP knowledge graph memory. Relations should be in active voice

Parameters* required

relationsarray

add_observationsAdd new observations to existing entities in your Memento MCP knowledge graph memory4 params

Add new observations to existing entities in your Memento MCP knowledge graph memory

Parameters* required

confidencenumber

Default confidence level (0.0 to 1.0) for all observations

metadataobject

Default metadata for all observations

observationsarray

strengthnumber

Default strength value (0.0 to 1.0) for all observations

delete_entitiesDelete multiple entities and their associated relations from your Memento MCP knowledge graph memory1 params

Delete multiple entities and their associated relations from your Memento MCP knowledge graph memory

Parameters* required

entityNamesarray

An array of entity names to delete

delete_observationsDelete specific observations from entities in your Memento MCP knowledge graph memory1 params

Delete specific observations from entities in your Memento MCP knowledge graph memory

Parameters* required

deletionsarray

delete_relationsDelete multiple relations from your Memento MCP knowledge graph memory1 params

Delete multiple relations from your Memento MCP knowledge graph memory

Parameters* required

relationsarray

An array of relations to delete

get_relationGet a specific relation with its enhanced properties from your Memento MCP knowledge graph memory3 params

Get a specific relation with its enhanced properties from your Memento MCP knowledge graph memory

Parameters* required

fromstring

The name of the entity where the relation starts

relationTypestring

The type of the relation

tostring

The name of the entity where the relation ends

update_relationUpdate an existing relation with enhanced properties in your Memento MCP knowledge graph memory1 params

Update an existing relation with enhanced properties in your Memento MCP knowledge graph memory

Parameters* required

relationobject

read_graphRead the entire Memento MCP knowledge graph memory system1 params

Read the entire Memento MCP knowledge graph memory system

Parameters* required

random_stringstring

Dummy parameter for no-parameter tools

search_nodesSearch for nodes in your Memento MCP knowledge graph memory based on a query1 params

Search for nodes in your Memento MCP knowledge graph memory based on a query

Parameters* required

querystring

The search query to match against entity names, types, and observation content

open_nodesOpen specific nodes in your Memento MCP knowledge graph memory by their names1 params

Open specific nodes in your Memento MCP knowledge graph memory by their names

Parameters* required

namesarray

An array of entity names to retrieve

semantic_searchSearch for entities semantically using vector embeddings and similarity in your Memento MCP knowledge graph memory6 params

Search for entities semantically using vector embeddings and similarity in your Memento MCP knowledge graph memory

Parameters* required

entity_typesarray

Filter results by entity types

hybrid_searchboolean

Whether to combine keyword and semantic search (default: true)

limitnumber

Maximum number of results to return (default: 10)

min_similaritynumber

Minimum similarity threshold from 0.0 to 1.0 (default: 0.6)

querystring

The text query to search for semantically

semantic_weightnumber

Weight of semantic results in hybrid search from 0.0 to 1.0 (default: 0.6)

get_entity_embeddingGet the vector embedding for a specific entity from your Memento MCP knowledge graph memory1 params

Get the vector embedding for a specific entity from your Memento MCP knowledge graph memory

Parameters* required

entity_namestring

The name of the entity to get the embedding for

get_entity_historyGet the version history of an entity from your Memento MCP knowledge graph memory1 params

Get the version history of an entity from your Memento MCP knowledge graph memory

Parameters* required

entityNamestring

The name of the entity to retrieve history for

get_relation_historyGet the version history of a relation from your Memento MCP knowledge graph memory3 params

Get the version history of a relation from your Memento MCP knowledge graph memory

Parameters* required

fromstring

The name of the entity where the relation starts

relationTypestring

The type of the relation

tostring

The name of the entity where the relation ends

get_graph_at_timeGet your Memento MCP knowledge graph memory as it existed at a specific point in time1 params

Get your Memento MCP knowledge graph memory as it existed at a specific point in time

Parameters* required

timestampnumber

The timestamp (in milliseconds since epoch) to query the graph at

get_decayed_graphGet your Memento MCP knowledge graph memory with confidence values decayed based on time2 params

Get your Memento MCP knowledge graph memory with confidence values decayed based on time

Parameters* required

decay_factornumber

Optional decay factor override (normally calculated from half-life)

reference_timenumber

Optional reference timestamp (in milliseconds since epoch) for decay calculation

Readme

Memento — Remember Everything, Forget Nothing

Memento

Give your AI tools a persistent memory — so every session starts where the last one left off.

Your 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.

Quick Start

View the full README on GitHub

Details

Repository: github.com/scrypster/memento
Website: github.com/scrypster/memento
Categories: AI & LLM Tools, Documents & Knowledge, Search & Web Crawling
Package: ghcr.io/scrypster/memento:0.1.0
Transport: STDIO
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Mindpmumitkavala/mindpmProject memory and a control plane for AI coding agents.9stars

Mcp Context Serveralex-feel/mcp-context-serverAn MCP server that provides persistent multimodal context storage for LLM agents.8stars

Citation Intelligenceautomatelab-tech/citation-intelligenceCheck what Perplexity, Claude, ChatGPT, Gemini, and Google AI Overviews cite for any query.8stars

Media Gen Mcpstrato-space/media-gen-mcpMCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation.8stars

HTML/CSS to Image APIhtmlcsstoimage/agent-pluginsGenerate images and PDFs from HTML/CSS, live websites, and reusable templates.0stars

Cairnjasondostal/cairn-mcpPersistent memory for AI agents and humans. Store, search, and discover patterns.7stars