이것은 우리 모델인 driaforall/mem-agent의 MCP 서버로, Claude Desktop이나 Lm Studio 같은 앱에 연결해 흑요석 같은 메모리 시스템과 상호작용할 수 있습니다.

지원 플랫폼

• macOS (메탈 백엔드)
• 리눅스 (GPU, vLLM 백엔드 포함)

플랫폼 노트: aarch64 (ARM64) 리눅스

• ARM64 리눅스에서는 빌드 실패를 방지하기 위해 기본적으로 vLLM이 설치되지 않습니다(안정적인 휠과 소스 빌드는 실패할 수 없습니다).
• vLLM 없이도 설치가 성공할 수 있습니다; 다음과 같은 방법이 있습니다:
• 기본 OpenRouter/OpenAI 경로(로컬 vLLM 필요 없음) 또는
• 호환 가능한 x86_64 호스트에서 vLLM을 실행하고 클라이언트를 그 호스트로 가리킵니다(agent/model.py create_vllm_client 참조).

진행 지침

LiteLLM 프록시 사용 (OpenAI 호환)

• 로컬(예: 포트 4000)에서 LiteLLM 프록시가 실행 중이라면, .env로 클라이언트를 구성하세요:

• 연결성 검증:

• 다음 중 하나를 사용하세요:

• CLI: make chat-cli

• MCP STDIO: make serve-mcp

• HTTP를 통한 MCP: make serve-mcp-http

참고: ARM64 리눅스에서는 vLLM 대신 이 설정이 권장됩니다.

1. make check-uv (UV가 설치되어 있다면 이 단계를 건너뛰세요).
2. make install: LmStudio MacOS에 설치.

mem-agent-mcp

This is an MCP server for our model driaforall/mem-agent, which can be connected to apps like Claude Desktop or Lm Studio to interact with an obsidian-like memory system.

Supported Platforms

• macOS (Metal backend)
• Linux (with GPU, vLLM backend)

Platform note: aarch64 (ARM64) Linux

• On ARM64 Linux, vLLM is not installed by default to avoid build failures (no stable wheels and source builds can fail).
• Installation will succeed without vLLM; you can:
  • Use the default OpenRouter/OpenAI path (no local vLLM needed), or
  • Run vLLM on a compatible x86_64 host and point the client at it (see agent/model.py create_vllm_client).

Running Instructions

Using a LiteLLM proxy (OpenAI-compatible)

• If you have a LiteLLM proxy running locally (e.g., on port 4000), configure the client via .env:

VLLM_HOST=localhost
VLLM_PORT=4000

• Verify connectivity:

curl http://localhost:4000/v1/models

• Then use either of these:
  • CLI: make chat-cli
  • MCP over STDIO: make serve-mcp
  • MCP over HTTP: make serve-mcp-http

Note: On ARM64 Linux, this is the recommended setup instead of vLLM.

1. make check-uv (if you have uv installed, skip this step).
2. make install: Installs LmStudio on MacOS.
3. make setup: This will open a file selector and ask you to select the directory where you want to store the memory.
4. make run-agent: If you’re on macOS, this will prompt you to select the precision of the model you want to use. 4-bit is very usable as tested, and higher precision models are more reliable but slower.
5. make generate-mcp-json: Generates the mcp.json file. That will be used in the next step.
6. Instructions per app/provider:
   • Claude Desktop:
     • Copy the generated mcp.json to the where your claude_desktop.json is located, then, quit and restart Claude Desktop. Check this guide for detailed instructions.
   • Lm Studio:
     • Copy the generated mcp.json to the mcp.json of Lm Studio. Check this guide for detailed instructions. If there are problems, change the name of the model in .mlx_model_name (found in the root of this repo) from mem-agent-mlx-4bit or mem-agent-mlx-8bit to mem-agent-mlx@4bit or mem-agent-mlx@8bit respectively.

Memory Instructions

• Each memory directory should follow the structure below:

memory/
    ├── user.md
    └── entities/
        └── [entity_name_1].md
        └── [entity_name_2].md
        └── ...

• user.md is the main file that contains information about the user and their relationships, accompanied by links to the enity file in the format of [[entities/[entity_name].md]] per relationship. The link format should be followed strictly.
• entities/ is the directory that contains the entity files.
• Each entity file follows the same structure as user.md.