Store and retrieve persistent knowledge across AI conversations using a local-first knowledge graph with hybrid search. Built for developers who need AI tools to remember context and facts between sessions.
io.github.scrypster/memento
Local install
STDIO
No auth required
How models use it and what it is built for.
Store and retrieve persistent knowledge across AI conversations using a local-first knowledge graph with hybrid search. Built for developers who need AI tools to remember context and facts between sessions.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Memento.
Paste any of these into Agent Studio after connecting Memento.
Common questions about connecting and running Memento.
What is a knowledge graph and how does Memento use it?
A knowledge graph stores facts and relationships between entities in a structured way. Memento uses it as a local-first database so your AI tools can persistently remember information across conversations without relying on external services.
How do I install and run Memento?
Use Docker: `docker run ghcr.io/scrypster/memento:0.1.0`. It runs via stdio transport, meaning it communicates with your MCP client through standard input/output streams.
Is my data stored locally or in the cloud?
Memento is local-first, meaning your knowledge graph and memories are stored on your machine by default. You maintain full control over your data.
What does 'hybrid search' mean in Memento?
Hybrid search combines multiple search methods (likely semantic and keyword-based) to find relevant memories. This helps you retrieve information even when you don't remember exact terms or relationships.
Can I use Memento with multiple AI tools or just one?
As an MCP server, Memento can be connected to any MCP-compatible AI tool or application, allowing you to share persistent memory across multiple tools and workflows.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams