by AskTheWay
Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.
# Add to your Claude Code skills
git clone https://github.com/AskTheWay/dsh-auto-memoryGuides for using ai agents skills like dsh-auto-memory.
Last scanned: 10/2/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-02T10:20:28.706Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how dsh-auto-memory compares with popular alternatives.
dsh-auto-memory is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by AskTheWay. Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services. It has 111 GitHub stars.
Yes. dsh-auto-memory passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/AskTheWay/dsh-auto-memory" and add it to your Claude Code skills directory (see the Installation section above).
dsh-auto-memory is primarily written in TypeScript. It is open-source under AskTheWay on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh dsh-auto-memory against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
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.

0.7 — update-replace semantics: consolidation updates facts in place instead of piling up near-duplicates, with a matching core shared between product and eval harness. Verified against the official desktop client (0.2.0-rc.2). Full history: CHANGELOG.md · Releases
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:
Injection cost is a flat line — measured on the real render path (typical ~40-char descriptions, default 4 KB budget):
| memories | 0 | 10 | 20 | 50 | 100 | 200 |
|---|---|---|---|---|---|---|
| injected section | 0 B | 2.3 KB (~564 tok) | 3.2 KB (~801 tok) | 4.0 KB (~1008 tok) | 4.0 KB | 4.0 KB |
The byte budget is a hard ceiling — from 50 memories on, the section is pinned at the cap no matter how many exist (oldest/lowest-ranked rows truncate with a marker). An empty store injects 0 bytes: the whole section disappears.
Compaction-proof by construction: the index rides in a dynamic system-prompt section re-evaluated on every step assembly — context compaction only compresses conversation history, so memories survive every compaction without re-injection tricks. Approaches that store memories as session-log messages lose theirs on the first compaction pass.
Eviction never misfires: four-class mixed scenario — only stale-zero-read memories get hidden; zero files lost; one read revives.
Known limitation, pinned as baseline: budget truncation is currently positional (index order), not relevance-ranked — probe retention under half-budget pressure drops to ~38%→10% as N grows. Pinning fixes it for what matters: pinned probes retain ≥80% at the same budget (0.3.0); full relevance ranking remains on the roadmap.
This evaluation layer already caught a real bug: the byte budget used to exclude the policy text, overshooting by ~800 bytes (fixed, regression-tested).
Verified platform matrix (manually tested, not just declared):
| CLI | Desktop | Web profile | |
|---|---|---|---|
| dsh version | 0.1.5-rc.2 | 0.2.0-rc.2 | 0.2.1-rc.2 |
| status | ✓ tools/prompt/consolidation | ✓ panel + import + audit | ✓ panel + import |
150 tests + three eval layers (L0 deterministic / L1 recall / L3 consolidation). 0 runtime deps beyond yaml, ~35 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). Works with
the official desktop client — verified on 0.2.0-rc.2.
Override in your profile's cordis.patch.yml (config replaces wholesale):
- id: auto-memory
config:
maxBytes: 4096 # injection budget (index + guidance + wrapper)
memoryDir: D:/memories # default: $DSH_HOME/memory
enableUserScope: true # false: user layer off on every path
autoSummarize: false # true: on root-session end, a background LLM files durable new facts
autoSummarizeMaxMemories: 5 # cap per consolidation
autoSummarizeMaxTokens: 2048 # consolidation output cap
staleAfterDays: 0 # >0: soft-hide zero-read memories older than N days (files kept)
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 · postmortem: shipping a PR to awesome-dsh-plugin
Per-version notes: CHANGELOG.md · GitHub Releases
MIT