Ori-Mnemos MCP
Local-first persistent agentic memory infrastructure powered by Recursive Memory Harness (RMH). It implements human cognition as mathematical models on a knowledge graph, supporting identity, knowledge graph construction, and semantic search for AI agents.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Implement persistent memory across sessions for AI agents
- Build knowledge graphs using wiki-links as graph edges
- Perform semantic search and retrieval over local markdown data
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
ori-memory 0.3.0
{
"version": "0.3.0",
"transport": "stdio",
"identifier": "ori-memory",
"registryType": "npm"
}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": {
"ori-mnemos-mcp": {
"command": "npx",
"args": [
"-y",
"ori-memory@0.3.0"
]
}
}
}Cline
{
"mcpServers": {
"ori-mnemos-mcp": {
"command": "npx",
"args": [
"-y",
"ori-memory@0.3.0"
]
}
}
}VS Code
{
"servers": {
"ori-mnemos-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ori-memory@0.3.0"
]
}
}
}Claude Desktop
{
"mcpServers": {
"ori-mnemos-mcp": {
"command": "npx",
"args": [
"-y",
"ori-memory@0.3.0"
]
}
}
}Let your agent find its tools
Find servers like Ori-Mnemos MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.