@bleed00/dsh-claude-mem
一个 DeepSeek Harness 插件，通过本地 claude-mem worker 的 HTTP API 集成 claude-mem：查询、上下文注入、手动保存和会话生命周期管理
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add @bleed00/dsh-claude-mem@0.1.5Claude Mem 以 @bleed00/dsh-claude-mem 发布，当前版本为 0.1.5。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
A DeepSeek Harness plugin that integrates claude-mem: query persisted cross-session memory, inject per-project context at session start, save manual memories, and drive session summarization — all through a local claude-mem worker's HTTP API.
It registers the model-facing tools mem_search, mem_timeline, mem_get_observations, mem_save, and mem_context, the mem-search skill, and the lifecycle hooks (agent/session-start context injection, optional tools/post-execute ingestion, optional agent/turn-stopping summarization). It is a single self-contained package with no monorepo-only dependencies.
One-liner with npx (no global install — npx fetches the dsh launcher and
dsh plugin forwards add to pnpm in the target profile):
npx -y @deepseek-ai/dsh plugin --profile demo add @bleed00/dsh-claude-mem
If you already have dsh on PATH, the same command without npx:
dsh plugin --profile demo add @bleed00/dsh-claude-mem
npm (recommended — ships prebuilt lib/, no build permission needed):
npx -y @deepseek-ai/dsh plugin --profile demo add @bleed00/dsh-claude-mem
GitHub (sources; runs a prepare build on first install):
npx -y @deepseek-ai/dsh plugin --profile demo add github:Bleed00/dsh-claude-mem
A GitHub install fetches sources, not build output, so pnpm runs this package's prepare script to build from src/. pnpm ≥10 refuses to run a git dependency's prepare until it is allowlisted; the first add fails and points at the fix — copy the exact package key pnpm printed into the profile's pnpm-workspace.yaml:
allowBuilds:
'@bleed00/dsh-claude-mem': true
then re-run the add. Treat that allowance as permission to run this package's code at install time; pin a commit for reproducible installs:
dsh plugin --profile demo add github:Bleed00/dsh-claude-mem#<sha>
Local checkout:
dsh plugin --profile demo add ./dsh-claude-mem
dsh on PATH.http://127.0.0.1:37700). Override with the baseUrl config or the DSH_MEM_BASE_URL environment variable.| Field | Default | Description |
|---|---|---|
baseUrl | http://127.0.0.1:<37700 + uid % 100> | Worker base URL. |
timeoutMs | 30000 | Per-request timeout (ms). |
dedupe | true | Collapse duplicate observations in query results (content fingerprint, never identity). |
platformSource | unset | Optional platform filter; omitted = search all memory. |
project | unset | Project name; defaults to the session cwd basename. |
injectContext | true | Inject session-start context. |
ingest | false | Save observed tool results as memories. |
summarize | false | Summarize sessions on turn stop. |
toolFilter.names | read, write, edit, bash | Tools observed when ingest is true. |
Platform scoping is a signal, never a restriction: default requests are unfiltered, and platformSource only adds an opt-in filter.
The worker can persist the same observation many times (a boilerplate "session
initiated" record, or a re-run tool result) — identical content, different id.
With dedupe: true (the default), query results collapse those copies: an
observation's content fingerprint is built from title + subtitle +
text + narrative + facts (normalized), so two entries that merely share a
generated title but differ in narrative are kept. The first copy (lowest id)
is retained. Structured results (mem_get_observations) are deduplicated by
fingerprint; rendered index/text results are deduplicated by exact rendered
row. Set dedupe: false to see the raw, unfiltered results.
cordis.patch.yml- id: claude-mem
config:
baseUrl: http://127.0.0.1:37700
platformSource: dsh
ingest: true
summarize: true
| Tool | Purpose |
|---|---|
mem_search | Search memory; returns an index (ids, titles, types). |
mem_timeline | Get context around one observation. |
mem_get_observations | Fetch full details for ids. |
mem_save | Save one manual memory. |
mem_context | Render the worker's session-start context text. |
The mem-search skill teaches the model the search → filter → fetch workflow that keeps token usage low.
pnpm install
pnpm run build # tsc + tsdown → lib/index.js
pnpm test
The package targets Node ≥ 20.12, TypeScript 6.0, and is authored against the @deepseek-ai/* framework packages (cordis, schemastery, dsh-tools, dsh-llm, dsh-skill, dsh-agent).
Apache-2.0 © Bleed00