Skip to content
VS Code

a mem mcp for VS Code

io.github.diaaaj/a-mem-mcp

Self-evolving memory system for AI agents

client:VS Code transport:stdio runtime:pypi

Install a mem mcp in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "llm-backend",
      "description": "LLM_BACKEND",
      "password": true
    },
    {
      "type": "promptString",
      "id": "llm-model",
      "description": "LLM_MODEL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "openai-api-key",
      "description": "OPENAI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "embedding-model",
      "description": "EMBEDDING_MODEL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "chroma-db-path",
      "description": "CHROMA_DB_PATH",
      "password": true
    }
  ],
  "servers": {
    "a-mem-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "a-mem"
      ],
      "env": {
        "LLM_BACKEND": "${input:llm-backend}",
        "LLM_MODEL": "${input:llm-model}",
        "OPENAI_API_KEY": "${input:openai-api-key}",
        "EMBEDDING_MODEL": "${input:embedding-model}",
        "CHROMA_DB_PATH": "${input:chroma-db-path}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

a mem mcp in other clients