知识图谱记忆服务

pip install graph-mem

graph-mem install opencode      # OpenCode
graph-mem install claude        # Claude Code
graph-mem install cursor        # Cursor
graph-mem install windsurf      # Windsurf
graph-mem install codex         # Codex CLI
graph-mem install gemini        # Gemini CLI
graph-mem install copilot       # GitHub Copilot
graph-mem install amp           # Amp
graph-mem install kiro          # Kiro
graph-mem install roocode       # Roo Code
graph-mem install trae          # Trae
graph-mem install augment       # Augment
graph-mem install continue      # Continue
graph-mem install warp          # Warp
graph-mem install kilocode      # KiloCode
graph-mem install qoder         # Qoder
graph-mem install codebuddy     # CodeBuddy
graph-mem install droid         # Droid (Factory)
graph-mem install antigravity   # Antigravity

{
  "mcpServers": {
    "graph-mem": {
      "command": "graph-mem",
      "args": ["server"]
    }
  }
}

{
  "mcpServers": {
    "graph-mem": {
      "command": "graph-mem",
      "args": [
        "server",
        "--project-dir", "/path/to/my/project",
        "--embedding-model", "sentence-transformers/all-mpnet-base-v2",
        "--use-onnx",
        "--cache-size", "20000",
        "--log-level", "INFO"
      ]
    }
  }
}

I want you to give yourself persistent memory using graph-mem. Run the following:

pip install graph-mem
graph-mem install opencode    # or: claude, cursor, windsurf, codex, gemini, copilot, amp, kiro, roocode, trae, augment, continue, warp, kilocode, qoder, codebuddy, droid, antigravity

This installs a skill file that teaches you how to use all 28 MCP tools.
The server should already be configured in your MCP config. If not, add it:

{
  "mcpServers": {
    "graph-mem": {
      "command": "graph-mem",
      "args": ["server", "--project-dir", "/path/to/your/project"]
    }
  }
}

Now start using the knowledge graph:

1. read_graph() to see current state
2. search_nodes("relevant topic") to find existing knowledge
3. add_entities, add_relationships, add_observations as you learn things
4. update_observation / update_relationship to fix mistakes in-place
5. open_dashboard() to explore the graph visually in your browser
6. At session end, capture anything important you discovered

Your goal: build a rich knowledge graph of this project so future sessions
start with full context instead of from zero. Search before adding to avoid
duplicates. Be specific with entity names and types.

pip install graph-mem
graph-mem server

uvx graph-mem server

git clone https://github.com/Sathvik-1007/GraphMem-MCP
cd graph-mem
pip install -e ".[full,dev]"
graph-mem server

pip install "graph-mem[embeddings]"   # sentence-transformers for local embeddings
pip install "graph-mem[onnx]"         # ONNX runtime for ~3x faster inference
pip install "graph-mem[ui]"           # aiohttp for interactive graph visualisation
pip install "graph-mem[full]"         # all of the above

graph TD
    Agent[Any MCP-Compatible Agent or IDE] --> Transport

    subgraph Transport
        STDIO[stdio]
        SSE[SSE]
        HTTP[streamable-http]
    end

    Transport --> Tools

    subgraph Tools[Graph-Mem MCP Server — 28 MCP Tools]
        Write[Write · 10 tools]
        Read[Read · 9 tools]
        Maint[Maintenance · 4 tools]
        Graph[Multi-Graph · 4 tools]
        UI[Dashboard · 1 tool]
    end

    Write --> Engines
    Read --> Engines
    Maint --> Engines

    subgraph Engines
        GE[GraphEngine]
        SE[HybridSearch]
        EE[EmbeddingEngine]
        GT[GraphTraversal]
        EM[EntityMerger]
    end

    Engines --> Storage

    subgraph Storage[SQLite Storage]
        DB[SQLite WAL]
        VEC[sqlite-vec]
        FTS[FTS5]
    end

    UI --> Dashboard[React SPA + aiohttp]
    Dashboard --> DB

graph-mem ui                              # open interactive graph explorer
graph-mem ui --no-open                    # start server without opening browser
graph-mem ui --port 9090                  # use a specific port
graph-mem ui --graph harry-potter         # open a specific named graph

graph-mem server                          # stdio transport (default)
graph-mem server --transport sse          # SSE transport
graph-mem server --db /path/to/graph.db   # custom database path
graph-mem server --project-dir /my/project  # store memory in <dir>/.graphmem/
graph-mem server --project-dir /my/project --graph harry-potter  # use named graph

# Embedding customization
graph-mem server --embedding-model sentence-transformers/all-mpnet-base-v2
graph-mem server --no-onnx --embedding-device cuda
graph-mem server --cache-size 50000

# Tuning
graph-mem server --search-limit 20 --max-hops 6
graph-mem server --log-level DEBUG

graph-mem install <agent>                 # project-level install
graph-mem install <agent> --global        # global/user-level install
graph-mem install <agent> --domain code   # use domain overlay (code, research, general)

graph-mem init                            # create .graphmem/ directory
graph-mem init --project-dir /my/project  # create in specific directory
graph-mem init --graph research           # create a named graph
graph-mem status                          # print graph statistics
graph-mem status --json                   # graph statistics as JSON
graph-mem status --graph research         # status of a named graph
graph-mem export --format json            # export entire graph
graph-mem export --output backup.json     # export to file
graph-mem import graph.json               # import graph from file
graph-mem validate                        # run integrity checks

git clone https://github.com/Sathvik-1007/GraphMem-MCP
cd graph-mem

# Using uv (recommended)
uv venv
uv pip install -e ".[full,dev]"

# Or using pip
python -m venv .venv
source .venv/bin/activate
pip install -e ".[full,dev]"

pytest                            # all tests
pytest tests/test_graph/          # graph engine tests
pytest tests/test_server/         # MCP server tool tests (all 28 tools)
pytest tests/test_cli/            # CLI command tests
pytest tests/test_models/         # data model tests
pytest tests/test_semantic/       # search + vector tests
pytest tests/test_storage/        # storage backend tests
pytest tests/test_db/             # database + migration tests
pytest tests/test_utils/          # config, logging, ID generation tests
pytest -x -q                      # stop on first failure, quiet output