io.github.sachitrafa/yourmemory

io.github.sachitrafa/yourmemory·v1.0.0·Memory & RAG

Quality Score

/100

Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.

Repository →

§01 Install

Claude Desktop (Docker)

{
  "mcpServers": {
    "yourmemory": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/sachitrafa/yourmemory:1.0.0"
      ],
      "env": {
        "DATABASE_URL": "<database_url>",
        "OLLAMA_URL": "<ollama_url>",
        "EXTRACT_MODEL": "<extract_model>"
      }
    }
  }
}

§02 Environment variables

DATABASE_URL

required

PostgreSQL connection string with pgvector. Example: postgresql://localhost:5432/yourmemory

OLLAMA_URL

Ollama server URL for local embeddings (nomic-embed-text) and classification (llama3.2:3b). Default: http://localhost:11434

EXTRACT_MODEL

Ollama model used for fact/assumption classification. Default: llama3.2:3b

§03 MCP Quality Score · methodology

freshness

completeness

installability

documentation

stability

§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

Memory for deep conversational context across any platform