io.github.sachitrafa/cognitive-ai-memory
Quality Score
84
/100
Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.
§01 Install
Claude Desktop (Docker)
{
"mcpServers": {
"cognitive-ai-memory": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/your-memory/cognitive-ai-memory:1.0.2"
],
"env": {
"DATABASE_URL": "<database_url>",
"OLLAMA_URL": "<ollama_url>",
"EXTRACT_MODEL": "<extract_model>"
}
}
}
}§02 Environment variables
DATABASE_URLrequired
PostgreSQL connection string with pgvector. Example: postgresql://localhost:5432/yourmemory
OLLAMA_URLOllama server URL for local embeddings (nomic-embed-text) and classification (llama3.2:3b). Default: http://localhost:11434
EXTRACT_MODELOllama model used for fact/assumption classification. Default: llama3.2:3b
§03 MCP Quality Score · methodology
freshness
24
completeness
10
installability
25
documentation
15
stability
10
§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