io.github.simplemindedbot/mnemex
Quality Score
68
/100
Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).
§01 Install
Claude Desktop (uvx)
{
"mcpServers": {
"mnemex": {
"command": "uvx",
"args": [
"mnemex"
],
"env": {
"MNEMEX_STORAGE_PATH": "~/.config/mnemex/jsonl",
"LTM_VAULT_PATH": "<ltm_vault_path>",
"MNEMEX_DECAY_MODEL": "power_law",
"MNEMEX_PL_HALFLIFE_DAYS": "3.0"
}
}
}
}§02 Environment variables
MNEMEX_STORAGE_PATHStorage path for short-term memory JSONL files
LTM_VAULT_PATHPath to Obsidian vault for long-term memory
MNEMEX_DECAY_MODELDecay model: power_law (default), exponential, or two_component
MNEMEX_PL_HALFLIFE_DAYSHalf-life in days for power-law decay model
§03 MCP Quality Score · methodology
freshness
13
completeness
10
installability
25
documentation
15
stability
5
§04 Alternatives in Memory & RAG
DoneThat
ai.donethat/donethat
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
Fodda Knowledge Graphs
ai.fodda/mcp-server
Expert-curated knowledge graphs for AI agents — PSFK Retail, Beauty, Sports and more.
ai.meminal/meminal
ai.meminal/meminal
Memory for deep conversational context across any platform