dsh-memory-forge
将记忆转化为 DeepSeek Harness 的技能：记录对话轮次，回忆重要内容，将流程整理为实际的 SKILL.md 文件
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:Ricky74192/dsh-memory-forge#677f171f7150b115022df5a707a6522fe57ee421Memory Forge 以 dsh-memory-forge 发布，当前版本为 0.1.1。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。
Memory that becomes skill for DeepSeek Harness (dsh).
dsh-memory-forge is a dependency-free Cordis Host plugin built around one loop: what happens in a session is captured, what is relevant to the next request is recalled, and what proved repeatable is forged into a real SKILL.md that the harness loads in later sessions.
<system-reminder> block, not a recency dump.memory_save, memory_search, memory_forget for explicit, model-driven use.memory_distill_skill turns a proven procedure into a SKILL.md bundle in the user skill root.Everything stays on the machine: JSONL under $DSH_HOME/memory, skills under $DSH_HOME/skills (or $DSH_AGENTS_HOME/skills). No network calls, no embedding service, no native modules.
DSH deliberately ships no memory plugin. It ships the primitives - AGENTS.md instruction loading, a skill registry that watches the filesystem, a plugin system with hot reload - but nothing that closes the loop from "what happened in this session" to "what the next session knows, and can do".
Hermes-style memory plugins (for example the MemOS local plugin) close that loop with an LLM + embedding + SQLite stack. dsh-memory-forge closes it with a much smaller footprint, and it closes it one step further:
| Hermes / MemOS local plugin | dsh-memory-forge |
|---|---|
| Full conversation capture, chunked and embedded | Turn capture into append-only JSONL; no embeddings |
| Auto-recall injected into the system context | Auto-recall injected as a durable user message before step 1 |
| Hybrid retrieval (FTS5 + vector, RRF, MMR, decay) | BM25-style lexical retrieval + query coverage + recency half-life |
memory_search / task_summary / skill_get | memory_search / memory_forget / memory_distill_skill |
| Task summarization pipeline | Not included; compaction already owns context compression |
| Skill auto-evolution (generate + upgrade) | Model-driven forging into real SKILL.md bundles, discovered by the harness |
| SQLite + bridge daemon + viewer | Plain files; read them with any editor |
The trade-off is explicit: no semantic search and no background summarization, in exchange for zero dependencies, zero daemons, a format you can git diff, and a plugin that installs into any DSH profile.
An unrelated package named dsh-memory exists on npm (SQLite FTS5 store, pinned-plus-recent recall). This project is independent and differs where it matters for retrieval: recall is query-relevant rather than recency-ordered, and procedures can be distilled into real skills.
Requires DSH with @deepseek-ai/dsh-base (any shipped profile: web, headless, tui, ...) and Node.js >= 22.
In the DSH Web UI, open Plugins -> Install bundle and point it at this directory, or ask a Creator-preset session to run:
plugin_manager action=install_bundle target=<absolute path to this checkout>
# once the npm release lands, the shortest path:
dsh plugin --profile <profile> add dsh-memory-forge
# straight from the repository:
dsh plugin --profile <profile> add git+https://github.com/Ricky74192/dsh-memory-forge.git
# without git installed, pin the release asset:
dsh plugin --profile <profile> add https://github.com/Ricky74192/dsh-memory-forge/releases/download/v0.1.1/dsh-memory-forge-0.1.1.tgz
The repository and archive installs were verified against this project; a bare dsh plugin add dsh-memory-forge requires the npm release.
The desktop profile is owned by the Electron application; use the Plugins page or plugin_manager for it instead of the CLI. dsh plugin forwards to pnpm, so pnpm must be on PATH. A file: dependency is installed as a copy, so reinstall after editing the checkout.
node scripts/dev-install.mjs --profile memdev --debug \
--memory-root "$PWD/.e2e/memory" \
--skills-root "$PWD/.e2e/agents-home/skills"
That copies this package into <DSH_HOME>/profiles/memdev/node_modules/dsh-memory-forge and writes the loader row. Remove it with --uninstall.
Installing the bundle inserts this row into the profile patch:
- insert:
- id: memory
name: 'dsh-memory-forge'
config:
maxRecallItems: 4
recallMinScore: 0.22
The row id stays memory, so overrides written for earlier versions keep working. With HMR enabled the plugin mounts immediately; otherwise restart the profile.
All keys are optional. Values are validated at activation and every correction is logged.
| Key | Default | Meaning |
|---|---|---|
memoryRoot | $DSH_HOME/memory | Root of the memory store. |
skillsRoot | $DSH_HOME/skills | Root receiving forged SKILL.md bundles. Set it to $DSH_AGENTS_HOME/skills to share skills with other agent tools. |
autoCapture | true | Capture conversation turns automatically. |
captureAssistant | true | Also capture the previous turn's assistant replies. |
minCaptureChars | 24 | Shorter messages are not captured automatically. |
maxCaptureChars | 4000 | Automatic capture truncates longer texts. |
maxRecallItems | 4 | Memories injected per recall. 0 disables recall. |
recallMinScore | 0.22 | Minimum relevance (0..1) to inject a memory. |
recallMaxChars | 2000 | Character budget of the whole injected block. |
halfLifeDays | 30 | Recency half-life; 0 disables recency weighting. |
includeGlobalScope | true | Recall entries saved with scope: 'global'. |
recallOn | first-step | first-step or every-step. |
debug | false | Write <memoryRoot>/debug.log diagnostics. |
| Tool | Purpose |
|---|---|
memory_save | Store one durable fact, preference, decision, or lesson. scope: 'global' for cross-project preferences. |
memory_search | Ranked search over the workspace and global namespaces. |
memory_forget | Delete a memory by id - preferred over writing a contradictory note. |
memory_distill_skill | Write a SKILL.md bundle from a proven procedure, recording the source memory ids. |
Tool descriptions carry the operating policy, so a session discovers when to save and recall without any prompt injection.
agent/pre-step (step 1)
|- capture user messages of this turn (from the decision's claimed batch)
| assistant messages of the previous turn (from the session log, seq-deduped)
|- recall query = newest user text
| rank(workspace + global) -> filter current-turn captures -> render block
'- inject append one `user` message with source kind `dsh-memory-forge`
Design decisions worth knowing:
user message, so it replays, compacts, and survives resume. The memory store is a derived index, never a second log.@deepseek-ai/dsh-skill-filesystem, and appear in the next session's catalogue - no registry API, no restart.$DSH_HOME/memory/
<workspace-key>/memories.jsonl # sha256(cwd)[0:16]
global/memories.jsonl # cross-project memories
debug.log # only with debug: true
$DSH_HOME/skills/<name>/SKILL.md # forged skills
Each line is one JSON object:
{"id":"mem_mvtaup5t_c19e0b","text":"...","kind":"note","tags":["build"],"importance":1,
"scope":"workspace","workspace":"4ae8d930ea1f76ea","createdAt":1792395281000,
"sessionId":"session-...","seq":12,"turn":1,"source":"auto-capture"}
The store tolerates damaged lines (it skips them with a warning) and rewrites atomically on delete.
node --test # 62 unit tests: retrieval, store, rendering, tools, skills, config
node scripts/e2e.mjs --profile memdev # 4 real headless turns against a mock provider
The offline end-to-end check runs actual harness turns with scripts/mock-provider.mjs, an Anthropic-Messages mock, and asserts from disk artifacts only:
memory_save through the real tool pipeline writes the memory;memory_distill_skill writes a valid SKILL.md;No API key is needed; the mock provider records every request body so assertions are made against what the model actually received.
The same four phases pass against the npm pack tarball installed with dsh plugin add file:<tgz>, which is the install path a registry package takes.
compaction plugin already owns context compression.autoCapture if that is unwanted.appendFileSync, so lines stay intact. Delete rewrites through a temp file.memory_stats tool and a compaction hook that expires superseded notes.The plugin stores conversation text locally; SECURITY.md states exactly what is written, where it lives, what becomes model-visible, and how to delete it.
MIT. See LICENSE.