How do I install cognitive-ai-memory?

Pick a client above and copy the generated config. Cursor and VS Code also have a deep link when the server can run locally or remotely.

Is cognitive-ai-memory official?

No. Registry-listed is not the same as vendor-official. Read the methodology for the difference.

How is the trust score calculated?

This listing scores 37 (Limited). The formula is published on the methodology page.

MCPpedia

cognitive-ai-memory MCP Server

Name: cognitive-ai-memory MCP Server
Author: sachitrafa

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

Tools Versions Alternatives

Registrysachitrafa

37Limited

Install

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "sachitrafa-cognitive-ai-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/your-memory/cognitive-ai-memory:1.0.2"
      ],
      "env": {
        "DATABASE_URL": "",
        "OLLAMA_URL": "",
        "EXTRACT_MODEL": ""
      }
    }
  }
}

Install guide

Related servers

SuperLocalMemory

78Good

Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.

Registryqualixar249 stars1.3K/wk

Codebase Memory

77Good

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

cognitive-ai-memory MCP Server | MCPpedia

Environment

Name	Required	Notes
DATABASE_URL	Yes	PostgreSQL connection string with pgvector. Example: postgresql://localhost:5432/yourmemory
OLLAMA_URL	No	Ollama server URL for local embeddings (nomic-embed-text) and classification (llama3.2:3b). Default: http://localhost:11434
EXTRACT_MODEL	No	Ollama model used for fact/assumption classification. Default: llama3.2:3b

cognitive-ai-memory MCP Server

Install

Related servers

SuperLocalMemory

Codebase Memory

Environment

Tools

About

FAQ

Reviews

haiku.rag

openInvest

M3 Memory

Codigest