dsh-auto-memory
适用于 DeepSeek Harness 的 Claude Code 风格自动记忆插件：按类型划分的记忆文件，以及自动注入系统提示词的 MEMORY.md 索引
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:AskTheWay/dsh-auto-memory#22b30e7651808ce5c6a858d9e53ce61497fe0e66Auto Memory 以 dsh-auto-memory 发布，当前版本为 0.3.0。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。
正在加载相关插件…
Your dsh agent forgets everything you tell it. Every. Single. Session.
Fix it with one command. Claude Code-style persistent memory for DeepSeek Harness — native, zero servers, zero embeddings, zero setup.
dsh plugin --profile demo add dsh-auto-memory
Say "Remember: I'm a Python backend engineer preparing for interviews" today — open a brand-new session tomorrow, ask "what do you know about me?", and it remembers.
pinned: true on memory_write): pinned entries lead
the index, survive budget truncation, and are exempt from staleness
eviction — a trust anchor the user controls.autoSummarize: true): when a root session ends, a
background LLM pass extracts durable new facts from the session and files
them as memories — deduplicated, capped, fully silent on failure. Claude
Code doesn't do this automatically.memory_read counts references; staleAfterDays
soft-hides zero-reference stale memories from the injected index (files
kept); memory_prune lists (dry-run) or deletes aged memories.memory_read resolves [[name]] cross-links one
level and attaches linked summaries.memory_delete_all — guarded by tools/pre-execute human approval:
the model cannot self-confirm irreversible bulk deletes.clear
(no concurrent-write escape), conditional index rebuild on touch
(no O(N) amplification), session-start stale refresh, subagent capture
cleanup, abortable consolidation.Tools: memory_write / memory_read / memory_list / memory_delete /
memory_prune / memory_delete_all.
DeepSeek Harness is the hottest open agent harness on GitHub right now — models, tools, sandboxes, everything is a plugin. But it ships with no memory subsystem at all. The official answer is three default-off MCP configs to third-party servers, which the official docs themselves qualify: not auto-injected, no forgetting policy, substring-only search. Your agent has amnesia by design.
dsh-auto-memory closes that gap natively:
| MCP bridge approach | dsh-auto-memory | |
|---|---|---|
| Memories injected into every system prompt, automatically | ✗ | ✓ (zero tokens when empty) |
| Typed memories: user / feedback / project / reference | ✗ | ✓ |
| Workspace + user scope layers — no cross-project leakage | ✗ | ✓ |
| Crash & concurrency safety (cross-process locks, orphan recovery) | — | ✓ |
| External services / databases / embeddings required | ✓✓✓ | none — just plain Markdown files |
Memories are ordinary files under $DSH_HOME/memory/ — hand-editable,
grep-able, git-friendly, yours.
node scripts/demo.mjs # no API key, no browser: watch write → index → inject → recall → forget
Or for real, in a chat: tell your agent things worth remembering. The model
calls memory_write / memory_read / memory_list / memory_delete,
following Claude Code's write discipline: dedupe-and-update over piling up,
absolute dates only, [[name]] cross-links, feedback memories carry
Why: / How to apply: lines.
Every request, one system-prompt section (order 4000) carries the index — re-evaluated per step, byte-budgeted, and gone entirely when the store is empty:
# Persistent memory index
## Project memories
- [压测过 PostgreSQL](id-generator-benchmark.md) — psycopg2 连接池有踩坑经验 (2026-09)
- [用户是 Python 后端工程师](user-prefers-python.md) — 正在准备面试; 偏好中文交流
Chinese titles, YAML frontmatter, one file per memory — exactly the Claude
Code MEMORY.md model, rebuilt natively on dsh's prompt-assembly pipeline.
This plugin survived a 12-agent adversarial code review (680k tokens of source-level scrutiny) before v0.1.0. Five production-grade traps were caught and fixed — with regression tests — including two that would have been field incidents:
memory collides with
MEMORY.md on case-insensitive filesystems — the write succeeds while
destroying the record. Blocked by a reserved-name guard.{{{ }}} braces in any memory
could crash every model request in the workspace — with no way for the
model to self-recover. Neutralized by a converging sanitizer.Plus: orphaned-lock self-healing (Ctrl+C can't brick your memory store), symlink-read protection, malformed-file tolerance, stable index ordering to protect KV-prefix caches, and a strict no-custom-session-events policy (they make dsh sessions refuse to resume).
A deterministic evaluation layer (evals/) runs in CI — no LLM, fully reproducible:
This evaluation layer already caught a real bug: the byte budget used to exclude the policy text, overshooting by ~800 bytes (fixed, regression-tested).
78 tests (incl. a deterministic eval layer). 0 runtime deps beyond yaml. 15 kB installed.
dsh plugin --profile demo add dsh-auto-memory # from npm (prebuilt)
dsh --profile demo # restart the profile
From source: npm install && npm run build && dsh plugin --profile demo add /abs/path.
Requires @deepseek-ai/dsh >= 0.1.5-rc.2 (Node ^22.19 || >=24).
Override in your profile's cordis.patch.yml (config replaces wholesale):
- id: auto-memory
config:
maxBytes: 4096 # injection budget
memoryDir: D:/memories # default: $DSH_HOME/memory
enableUserScope: true # false: user layer off on every path
execute → name normalized to [a-z0-9-] (reserved names
rejected) → cross-process file lock (official dsh-atomic-write) → atomic
write → full index rebuild inside the lock.{{.
Tool writes take effect on the very next request — no restart, ever.tool/call / tool/result.Deep dives: design decisions · dsh source-level research · postmortem: shipping a PR to awesome-dsh-plugin
MIT