Memento
Local-first, LLM-agnostic memory layer for AI assistants using a local SQLite database.
Memento is a local-first, LLM-agnostic memory layer for AI assistants that stores structured memories in a local SQLite database accessible to any MCP-compatible client. The system supports five typed memory kinds — fact, preference, decision, todo, and snippet — with append-only audit logs, conflict detection, and configurable memory decay. A browser-based dashboard provides local search, auditing, and memory pack management without telemetry or cloud dependencies.
Source
Repository: https://github.com/veerps57/memento
Maintain Memento?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Memento on getagentictools](https://getagentictools.com/mcp/veerps57-memento?ref=badge) Related mcp
Playwright Stealth Enables stealth web browsing automation with Playwright for tasks like navigation, form filling, and screenshot capture while avoi
Web Research Enables web browsing capabilities through Google searches and webpage content extraction using Playwright for browser automation a
Google Cloud Platform Integrates with Google Cloud Platform to enable natural language management of cloud resources including compute, storage, network
My Agent Browser Adds Chrome lifecycle management and fault recovery on top of chrome-devtools-mcp.
Cypress Test Generator Automates Cypress test generation by analyzing web pages with Puppeteer to extract DOM elements and generate structured page objec
Patchright Stealth Browser Provides stealth browser automation capabilities through a containerized server that avoids anti-bot detection systems while offer