ZenBrain MCP
An open-source agent memory system providing working, episodic, semantic, procedural, and core memory layers. It utilizes nine foundational neuroscience-grounded algorithms like Hebbian Learning and FSRS, orchestrated by a MemoryCoordinator that manages storage and recall across seven layers using local SQLite without requiring an account or cloud configuration.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Store and recall information using semantic memory layers
- Implement spaced repetition and forgetting curves via FSRS
- Simulate sleep consolidation for memory strengthening
- Manage cross-context memory retrieval for AI agents
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
@zensation/mcp 0.3.1
{
"version": "0.3.1",
"transport": "stdio",
"identifier": "@zensation/mcp",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "ZENBRAIN_DB",
"default": "./zenbrain.db",
"description": "Path to the SQLite file that holds the memory. A leading ~/ means your home directory; a relative path depends on where the client starts the server (some start it in /), so give an absolute or ~/ path. Use ':memory:' for a store that is discarded when the process exits."
},
{
"name": "ZENBRAIN_CONTEXTS",
"default": "personal,work,learning,creative",
"description": "Comma-separated context domains, passed to the cross-context layer. No tool uses that layer yet, so the value currently has no effect."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"zenbrain-mcp": {
"command": "npx",
"args": [
"-y",
"@zensation/mcp@0.3.1"
],
"env": {
"ZENBRAIN_DB": "<YOUR_ZENBRAIN_DB>",
"ZENBRAIN_CONTEXTS": "<YOUR_ZENBRAIN_CONTEXTS>"
}
}
}
}Cline
{
"mcpServers": {
"zenbrain-mcp": {
"command": "npx",
"args": [
"-y",
"@zensation/mcp@0.3.1"
],
"env": {
"ZENBRAIN_DB": "<YOUR_ZENBRAIN_DB>",
"ZENBRAIN_CONTEXTS": "<YOUR_ZENBRAIN_CONTEXTS>"
}
}
}
}VS Code
{
"servers": {
"zenbrain-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@zensation/mcp@0.3.1"
],
"env": {
"ZENBRAIN_DB": "<YOUR_ZENBRAIN_DB>",
"ZENBRAIN_CONTEXTS": "<YOUR_ZENBRAIN_CONTEXTS>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"zenbrain-mcp": {
"command": "npx",
"args": [
"-y",
"@zensation/mcp@0.3.1"
],
"env": {
"ZENBRAIN_DB": "<YOUR_ZENBRAIN_DB>",
"ZENBRAIN_CONTEXTS": "<YOUR_ZENBRAIN_CONTEXTS>"
}
}
}
}Let your agent find its tools
Find servers like ZenBrain MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.