Swd146296/dsh-memos-bridge ↗★ 2
dsh-memos-bridge
DeepSeek Harness bundle that bridges the MemOS memory service into the agent over MCP: add, search, update and manage memories as native tools (mcp__memos__*).
安装
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Swd146296/dsh-memos-bridge说明文档
阅读完整 README ↗Configuration
The bundle's patch inserts two rows: the memos-bridge provider (exposes memosBridge with the venv python, this package's runner path, and the MemOS cwd) and the memos-mcp @deepseek-ai/dsh-mcp-client row (serverName: memos) that spawns the runner over stdio. The runner preflights Neo4j (hard dependency: clear one-line error + fast exit), warns when the LLM/embedding gateway is down, and defaults the endpoints to 127.0.0.1 for host-run deployments.
Environment knobs read at mount time:
| Variable | Default | Meaning |
|---|---|---|
MEMOS_PYTHON | python | python of the MemOS venv |
MEMOS_HOME | '' (inherit cwd) | MemOS checkout used as the child cwd |
MEMOS_MCP_SERVER | memos | tool namespace (mcp____*) |
To change any other field (e.g. toolCallTimeoutMs, failOnStartupError), override the row by id in your profile's cordis.patch.yml — later layers win, but an id-targeted patch replaces the whole config, so restate every key:
- id: memos-mcp
config:
transport: stdio
serverName: memos
command: 'C:/path/to/MemOS/.venv/Scripts/python.exe'
args: ['C:/path/to/dsh-memos-bridge/scripts/memos_mcp_runner.py']
cwd: 'C:/path/to/MemOS'
toolCallTimeoutMs: 60000
failOnStartupError: false