Basic Memory
OfficialA knowledge management system that lets LLMs build and query a persistent graph of interconnected notes stored as local Markdown files. Features semantic search and can visualize connections between concepts.
What it does
- Write and update markdown notes with semantic content
- Search notes by meaning using vector similarity and keywords
- Build context from previous conversations to continue discussions
- Create visual concept maps with Obsidian canvas
- Track recent activity across knowledge projects
- Read and manage file contents by path or permalink
Best for
Tools (17)
Delete a note by title or permalink
Read a file's raw content by path or permalink
Build context from a memory:// URI to continue conversations naturally. Use this to follow up on previous discussions or explore related topics. Memory URL Format: - Use paths like "folder/note" or "memory://folder/note" - Pattern matching: "folder/*" matches all notes in folder - Valid characters: letters, numbers, hyphens, underscores, forward slashes - Avoid: double slashes (//), angle brackets (<>), quotes, pipes (|) - Examples: "specs/search", "projects/basic-memory", "notes/*" Timeframes support natural language like: - "2 days ago", "last week", "today", "3 months ago" - Or standard formats like "7d", "24h"
Get recent activity for a project or across all projects. Timeframe supports natural language formats like: - "2 days ago" - "last week" - "yesterday" - "today" - "3 weeks ago" Or standard formats like "7d"
Search across all content in the knowledge base with advanced syntax support.
