@ai4gensteam/dsh-agents-swarm
A source library for DeepSeek Harness: 72 feeds on an hourly timer, a reader with transcripts and translation, and a publisher that turns what it collects into a podcast, a digest, or a report
39 results
A source library for DeepSeek Harness: 72 feeds on an hourly timer, a reader with transcripts and translation, and a publisher that turns what it collects into a podcast, a digest, or a report
蜗蜗 (Sumikko Gurashi snail) desktop pet for the DeepSeek Harness Web UI: 8-direction crawling, slime trail, file-drop feeding, sleep, and conversation reactions
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
Unofficial Plannotator integration for DeepSeek Harness: annotate plans inline and return structured feedback to the waiting coding agent
Browser element annotation bridge for DeepSeek Harness
A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots.
DSH RSS 订阅工具插件:管理订阅源、OPML 导入导出、抓取解析 RSS/Atom 并保留正文(rss_list / rss_add / rss_remove / rss_fetch / rss_check / rss_opml_export / rss_opml_import)
Fully customizable keyboard shortcuts for the DeepSeek Harness WebUI — macOS-first defaults, 34 pre-registered features across session/view/clipboard/model/permission/system groups, one-click recording to add your own bindings, silent permission cycling with color feedback.
Agent trajectory governance & anomaly diagnosis for DeepSeek Harness: rebuild structured multi-branch trajectory trees from the session/event feed, keep observation-layer snapshots, and run three temporal anomaly strategies (loop deadlock / invalid retry / goal drift).
An eye that grows: accumulated design taste for DSH agents. A taste corpus + codified principles that sharpen with every example you feed — review designs against learned judgment, not a fixed ruler.
Agent-office dashboard for DeepSeek Harness (DSH): a 6-column sprite office visualizing workspaces, sessions, token usage and subagents — with built-in Agent Mail, Feishu/Lark message feed, meeting schedules, transcripts and an office log tab. One screen to see what every agent is doing, plus your mail, messages & meetings. 给 DeepSeek Harness 的「办公室」插件:工作区/会话/token/子代理/Agent邮箱/飞书消息/会议日程/妙记逐字稿/办公室日志一屏总览,一眼看穿每个 Agent 在忙什么。
Hatch a digital creature in your DeepSeek Harness. It feeds on your real work — turns, tool calls, even your errors — and evolves along branching lines shaped by how you actually work. Zero tokens, zero tools, the model never knows.
Web page reader for DeepSeek Harness (dsh): fetch any URL and extract clean markdown or plain text, inventory links, read RSS/Atom feeds, and inspect HTTP headers without the body — zero runtime dependencies
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
时事热点:AI 大事 + 工科热点 实时聚合面板(DeepSeek Harness Web 插件)。侧边栏入口 + 三视图面板 + 设置管理卡片,数据来自 dsh web 搜索缝合(含抖音/小红书/B站/知乎等来源标注)。
Diary Detective for DeepSeek Harness — a warm mirror that reads journals, illuminates blind spots, and gives gentle daily feedback. 赛博日记侦探:一面有温度的镜子,读日记、照见盲点、给温柔反馈。
dsh-langfuse: Langfuse LLM observability for DeepSeek Harness — one OpenTelemetry trace tree per agent session, with feedback scores and subagent lineage.
Zhihu (知乎) dashboard for DeepSeek Harness: hot list with trends, follow feed, post tracking, and app-idea distillation — from the UI and as native agent tools (zhihu_search/hot/answer/global_search/followees).
会话记忆 → OKF 知识沉淀插件:预测驱动的神经自我学习记忆系统。把会话中高价值内容按 OKF v0.1 规范沉淀为长期记忆,跨会话自动唤起。Session-to-OKF memory plugin with neuro-self-learning (predictive recall, uncertainty-driven capture, reinforcement feedback).
RSS/Atom feed subscription, scheduled fetching, deduplication, LLM-powered summarization, and daily Markdown digests — as a dsh (DeepSeek Harness) bundle.
dsh plugin: during long agent thinking, posts a hot-news or reminder message directly into the conversation stream.
喂食规则
Real-time code feedback for DeepSeek Harness — LSP, linters, formatters, type-checking, and structural analysis.
DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.