DSH Hub

highland0971/dsh-native-memory

dsh-native-memory

UIMemory0 GitHub stars· updated 2026-08-16

Native, per-workspace long-term memory for DeepSeek Harness: approval-gated writes, cited provenance, FTS cross-session recall — no external server, no extra runtime dependency.

Install

npx @deepseek-ai/dsh plugin --profile web add dsh-native-memory

Restart `dsh web` after install. Bundle APIs can change during the developer preview.

README badge

dsh-native-memory DSH Hub badge
[![DSH Hub](https://dshhub.dev/badge/dsh-native-memory.svg)](https://dshhub.dev/plugins/dsh-native-memory)

Paste this into your README. The star count updates with every catalog sync.

From the README

Excerpt from highland0971/dsh-native-memory, cleaned of badges and images.

dsh-native-memory

Native, per-workspace long-term memory for DeepSeek Harness (dsh): facts and profiles stored on the harness's own storage-domain, cross-session recall through session-query FTS, approval-gated writes, and cited provenance — no external server, no extra runtime dependency.

⚠️ Installing a plugin runs third-party code on your machine with your own permissions. Review the source (src/) and the security model before installing.

Why this one

dsh-hermes-memorydsh-native-memory
Storage~/.dsh/settings.yaml namespacededicated storage-domain unit (~/.dsh/storages/dsh_memory.json)
Scopeuser-global, all projectsper workspace (exact-cwd authorization)
Write safetysilent, model-onlyhuman approval gate + session-log audit
Recalleverything always injected (hard caps)bounded always-on profile plus on-demand recall + FTS over past sessions
Dependenciesvendored imports into the harness checkoutnone beyond zod + the harness itself

See docs/design.md for the full architecture and the competitive landscape analysis.

Install

dsh plugin --profile web add dsh-native-memory   # npm after release
dsh plugin --profile web add /path/to/this/repo  # from a checkout

Restart dsh web. The bundle enables session-query full-text search and adds the memory tools to every session. Details and configuration: docs/install.md.

Tools

ToolKindGate
memory_rememberadd/update a fact in this workspace (secrets rejected by default)approval
memory_editreplace a factapproval
memory_forgetarchive a fact (soft delete)approval
memory_recalldeterministic three-tier keyword scan (tags > text > fuzzy; freshness/access tie-breaks)none
memory_searchFTS over this workspace's past sessions (caller excluded)none
memory_expandexpand a fact's citation to the original log excerptnone
memory_consolidatenear-duplicate merge suggestions + cap budgetnone
memory_importimport candidate facts from a past session's logapproval (per fact)
memory_profileread the always-injected workspace profilenone
memory_exportwrite a git-friendly Markdown mirror (.dsh-memory/memory.md, masked, idempotent)none

Every fact records its origin (sessionId, seq) — memory stays reconstructable from the lossless session log.

Writes reject secret-shaped text (tokens / keys / passwords) by default; secretPolicy: "mask" | "off" in the bundle patch relaxes that. The credential-assignment detector can flag benign token: … values of ≥16 characters. Prompt injection and tool output always mask secrets.

A read-only browser page (settings → 记忆) lists every workspace's facts with secrets masked; deletions are copied as a memory_forget instruction and land in the chat through the approval gate.

Opt-in session-end proposals (proposeOnSessionEnd: true): one cheap LLM call distills a finished session into candidate facts shown in the next sessions; they become facts only through the approval-gated memory_remember.

A compaction drift guard (compactionGuard: true, on by default) surfaces literal anchors a compaction summary dropped, as data to verify in the next sessions — deterministic, no LLM.

Development

Related plugins