Last updated
March 16, 2026
MCP profile
Github Basicmachines Co Basic Memory
Local-first knowledge management with bi-directional LLM sync via Markdown files.
AI & Machine LearningPackagePythonOpen SourceExternal
Visibility
Public
ByRegistry
About This MCP Server
Let's say you're exploring coffee brewing methods and want to capture your knowledge. Here's how it works:
1. Start by chatting normally:
... continue conversation.
2. Ask the LLM to help structure this knowledge:
LLM creates a new Markdown file on your system (which you can see instantly in Obsidian or your editor):
Capabilities
Chat histories capture conversations but aren't structured knowledgeRAG systems can query documents but don't let LLMs write backVector databases require complex setups and often live in the cloudKnowledge graphs typically need specialized tools to maintainLocal-first: All knowledge stays in files you controlBi-directional: Both you and the LLM read and write to the same filesStructured yet simple: Uses familiar Markdown with semantic patternsTraversable knowledge graph: LLMs can follow links between topicsStandard formats: Works with existing editors like ObsidianLightweight infrastructure: Just local files indexed in a local SQLite databaseHave conversations that build on previous knowledgeCreate structured notes during natural conversations
Tools & Endpoints1
Why Use Github Basicmachines Co Basic Memory?
- Chat histories capture conversations but aren't structured knowledge
- RAG systems can query documents but don't let LLMs write back
- Vector databases require complex setups and often live in the cloud
- Knowledge graphs typically need specialized tools to maintain
- Local-first: All knowledge stays in files you control
- Bi-directional: Both you and the LLM read and write to the same files
- Structured yet simple: Uses familiar Markdown with semantic patterns
- Traversable knowledge graph: LLMs can follow links between topics
- Standard formats: Works with existing editors like Obsidian
- Lightweight infrastructure: Just local files indexed in a local SQLite database
- Have conversations that build on previous knowledge
- Create structured notes during natural conversations
Specifications
Status
live
Industry
AI & Machine Learning
Category
General
Server type
Package
Language
Python
License
Open Source
Verified
Yes
Requirements
- uv tool install basic-memory
Hosting
Hosting Options
- Package
API
Integrate this server into your application. Choose a connection method below.
1
Install
Install command
Python
uv tool install basic-memory2
Configure
Configuration
json
{
"mcpServers": {
"basic-memory": {
"command": "uvx",
"args": [
"basic-memory",
"mcp"
]
}
}
}Performance
Usage
Quick Reference
- Name
- Github Basicmachines Co Basic Memory
- Function
- Local-first knowledge management with bi-directional LLM sync via Markdown files.
- Available Tools
- basic-memory cloud set-key bmc_abc123...
- Transport
- Package
- Language
- Python
- Install
- uv tool install basic-memory
- Source
- External (Registry)
- License
- Open Source
Get started
Ready to integrate this MCP server?
Book a demo to see how this server fits your workflow, or explore the full catalog.