local-first 34

deja-vu memory for DeepSeek Harness: the session history of forty other coding agents, searchable and recalled before each step — a local index, no LLM.

PLUR memory for DeepSeek Harness — engrams injected straight into the prompt, no tool call required

Recent conversations stay vivid. Older ones fade into summaries, not oblivion. StrataGate gives DeepSeek Harness six-layer, time-decaying memory, while lasting events and relationships settle into a knowledge graph. Bring your memories from other AIs with

Turn explicit DSH session experience into reviewable native Skills

Local image-code knowledge library with native macOS and local Web clients, plus MCP and Skill for Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval

DeepSeek Harness (DSH) local-first cross-session project memory: bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings, external service or bundled runtime dependencies.

Excerpt-driven session branching and conversation lineage for DeepSeek Harness

查看、搜索和恢复已归档会话，支持未归档管理、工作区批量归档、备份、回收站与残留会话检查。

Local-first memory & context harness for coding agents

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

把 TiddlyWiki 5 变成你和 Agent 共用的本地文档中心（纯文本 + git）：你在 DSH 界面里阅读、写作、记日记，Agent 用 16 个 tiddlywiki_* 工具读写同一批笔记；每条笔记都是你能读、能改、能审计、能随时带走的文件——不是自动记忆插件，不做后台抓取。可选一键发布到微信公众号草稿箱。 Turn TiddlyWiki 5 into a document center you and your agent share, in plain text under git —

Local-first file conversion for DeepSeek Harness - images, PDF, data, audio/video and office documents. No API keys, no uploads, no token cost.

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

Local, per-session prompt stash for DeepSeek Harness Web

Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva

让智能体拥有自己的声音：它决定什么时候开口说话，你决定接不接（接听/拒接/稍后再说）。语音全部在本机合成，首次使用需要在设置卡里一键部署本地运行环境。

DSH Skill 智能实验室（DSH Skill Intelligence）：探索优秀 Agent Skill 的结构与方法，将成熟 AI 工作流转化为个人能力和企业业务能力。

A local-first, human-gated authorial film workflow for DeepSeek Harness

Evidence-backed, human-approved project memory for DeepSeek Harness

A structured work-state protocol for DeepSeek Harness agent handoffs

Human-editable notes, todos and documents for DeepSeek Harness, with search, tables, attachments, export and optional agent collaboration.

Evidence-governed experience memory for DeepSeek Harness

Native knowledge context for DeepSeek Harness

Adapt ERP: learn your ERP through the browser and build private local knowledge in DeepSeek Harness

DeepSeek Harness community Bundle for local, evidence-backed Agent Memory

Select and locally share one or more DeepSeek Harness conversation turns as Markdown, self-contained HTML, or a long PNG, with privacy-first redaction and no uploads

Approval-gated workspace instructions and memory for DeepSeek Harness

DSH input recorder & analyzer: local text capture (keyboard + UIA), daily/weekly stats, topic analysis and report export for daily reports. Privacy-first: local-only, password fields excluded, sensitive data redacted.

[支持 DSH 0.1.7–0.2.x / DSH 0.1.7–0.2.x compatible] Local file recall for DeepSeek Harness: it watches the folders you choose and keeps a SQLite index of what appeared — name, type, size, appeared-at, location and origin — so "where did I put that file?" be

Local-first DeepSeek Harness plugin marketplace with GitHub and dshfind providers

本地优先的 Harness 运行遥测插件：记录请求、模型、工具与插件生命周期指标（延迟、Token、成本、错误、缓存），默认不采集内容。Local-first Harness telemetry plugin for DeepSeek Harness. npm 包 dsh-local-telemetry（dsh-telemetry 名已被第三方占用）。

Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).

Local, read-only usage, activity, and performance analytics for DeepSeek Harness sessions.