Basic Memory is a local-first knowledge management system designed to create persistent, semantic graphs from AI conversations, storing data in Markdown files. It targets users who want to build a growing, interconnected knowledge base without relying on cloud services or complex setups, enabling LLMs to read and write to this local data.

How It Works

Basic Memory leverages the Model Context Protocol (MCP) to integrate with LLMs. It stores information as Markdown files, with specific frontmatter, observations (facts), and relations (links) defining a semantic graph. A local SQLite database indexes these files for efficient searching and retrieval. This approach allows LLMs to interact with a persistent, structured knowledge base directly through simple file operations and semantic links, facilitating context-aware conversations and knowledge synthesis.

Quick Start & Requirements

• Install via uv tool install basic-memory.
• Requires Claude Desktop or VS Code with MCP configuration.
• Documentation: https://memory.basicmachines.co

Highlighted Details

• Local-first knowledge management using Markdown files.
• Bidirectional read/write capabilities for LLMs and users.
• Semantic graph construction via structured observations and relations in Markdown.
• Real-time synchronization of local files.

Maintenance & Community

• Developed by Basic Machines.
• Contributions are welcome via a contributing guide.

Licensing & Compatibility

• License: AGPL-3.0.
• AGPL-3.0 is a strong copyleft license, requiring derivative works to also be open-sourced under AGPL-3.0. This may restrict commercial use or linking with closed-source applications.

Limitations & Caveats

The AGPL-3.0 license may impose significant restrictions on commercial adoption or integration into proprietary software. The project relies on specific LLM clients like Claude Desktop or VS Code configurations for its core functionality.