io.github.Hustada/collective-memory
Quality Score
80
/100
MCP server for persistent, semantic memory across AI sessions
§00 Trust verdict · v1 advisory · method
UNVERIFIEDno verdict on file
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
§01 Install
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"collective-memory": {
"command": "npx",
"args": [
"-y",
"collective-memory"
],
"env": {
"OPENAI_API_KEY": "<your-openai_api_key>"
}
}
}
}Cursor (.cursor/mcp.json)
{
"mcpServers": {
"collective-memory": {
"command": "npx",
"args": [
"-y",
"collective-memory"
],
"env": {
"OPENAI_API_KEY": "<your-openai_api_key>"
}
}
}
}Cline (cline_mcp_settings.json)
npx -y collective-memory§02 Environment variables
OPENAI_API_KEYrequiredsecret
OpenAI API key for generating embeddings
§03 MCP Quality Score · methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
5
§04 Alternatives in Memory & RAG
ai.butlerbrain/mcp
ai.butlerbrain/mcp
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
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.