@ddtcorex/dsh-maestro-supervisor
Supervisor daemon for DSH Web resilience — auto-detect crashes, rollback to LKG, report
111 results
Supervisor daemon for DSH Web resilience — auto-detect crashes, rollback to LKG, report
Mine local DSH session logs (JSONL) into personal 'usage & impact' receipts: Markdown day/week/month reports plus a self-contained HTML receipt, cross-referenced with local git log. Zero-network mining, privacy-first (reads only your own dshHome).
Notebook Knowledge Studio — NotebookLM-like local knowledge workspace for DeepSeek Harness: Notebooks, Sources, source-grounded Chat with citations, and Studio artifacts (Mind Map / Reports / Flashcards / Quiz / Infographic / Slide Deck / Data Table), stored as OKF v0.2 markdown under the workspace.
Give DeepSeek Harness a subconscious: it `dreams` asynchronously in the background, turning daily conversations and tool logs into dream reports presented in an immersive web interface
Token usage / cache-hit / duration report cards for DeepSeek Harness sessions, with optional cost estimation.
Auto type-check and lint diagnostics for DeepSeek Harness: after the model edits code, tsc runs in the background and a code_check tool reports what broke
DSH web plugin: a floating, resizable, multi-tab Markdown preview panel plus an md_preview model tool — preview any .md report right from the conversation, without opening local apps.
抖音本地推 OEM 投流日报/周报自动化插件:安装后自动把 douyin-oem-touliu-report 技能部署到用户技能根,采集抖音来客+巨量本地推三源数据并生成 docx 报告。Douyin local-promotion OEM ad-daily/weekly report automation: deploys the douyin-oem-touliu-report skill (collect 3 data sources, compute metrics, build docx reports).
Safe start/stop companion for dsh web: a bottom-right power dock in the Web UI that shuts the host down cleanly (response flush, port release, exit code 0) and reports the running dsh version.
Developer Wrapped for DeepSeek Harness — your coding journey with AI, visualized.
DSH plugin: a persistent, per-session Python interpreter provisioned with Biomni's biomedical tool library, plus a Settings section that reports what the interpreter can actually do.
Controlled A/B comparisons and evidence-backed reports for DeepSeek Harness plugins and presets.
Map-reduce council of subagents for the DeepSeek Harness: one task fans out to independent members, their findings are deduplicated, verified by a separate panel, and reduced to a quorum report
DSH Web plugin for Agent execution quality diagnosis reports.
面向 CSV 描述统计与可复现报告的 DeepSeek Harness 插件
Inline Command Code plan usage badge in the DSH composer toolbar (5h/weekly window usage + remaining credits) with an upward detail popover; reuses the commandcode/report remote from @mars-sea/dsh-commandcode-provider.
Neural Ledger · 神经账本 — turn your DSH collaboration sessions into a visual work ledger: token analytics, smart insights, trend forecasting, and one-click daily/weekly/monthly Markdown reports.
DSH (DeepSeek Harness) v0.1.x Cordis 插件:自动监听每轮模型 API 调用的缓存命中/未命中/输出 tokens,实时统计缓存命中率与按官方定价(含峰谷时段)预估的 API 费用,注册 cache_report 工具,并在浏览器每条消息末尾低调显示本轮 tokens 与人民币消耗。
vLLM-Ascend Profiler Analyzer — a DeepSeek Harness plugin that ingests vLLM-Ascend / Ascend NPU profiling artifacts, renders a standalone Host+Device swimlane / cost-share / optimization-advice surface, and exports Markdown or PDF reports.
DeepSeek Harness plugin: reports what changed in your authored pull requests since your last check — merged, closed, or gone stale.
A tamagotchi-style desktop pet for DeepSeek Harness — living skins that blink & wag, weather + time-of-day ambience, weekly report cards, a fetch mini-game, 24 collectible skins, achievements and synthesized sounds. 电子宠物:会眨眼摇尾巴、看天气看时辰、还能接球。
DSH-Plugin: minimal infrastructure entry — infra_status / infra_bootstrap tools that probe the mounted infra stack (memory, observability, search, skills) and report readiness.
Per-process tool-call statistics for DeepSeek Harness (not token usage): adds a tool_stats tool reporting call counts, error counts, and average durations.
Agent benchmark evaluation plugin for DeepSeek Harness: web panel, slash commands, headless CLI, test-set import, model/judge switching, orchestration, scoring, and reports.