dsh-qboson-ising-solver
QBoson Kaiwu/SPQC Ising Matrix solver plugin for DeepSeek Harness
204 results
QBoson Kaiwu/SPQC Ising Matrix solver plugin for DeepSeek Harness
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
为 DSH 的 pi-ai 第三方模型补充可配置的思考强度档位,并设置子 agent 默认思考强度。
SillyTavern prompt presets, macros and editor for DeepSeek Harness
DSH 图形化 Agent 配置台:可视化拼装提示词、工具、技能、子代理与备用模型,按预设绑定即接管;自建预设走平台的预设注册入口,所有配置存在插件自己的数据里,卸载即恢复原状。
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
DSH 提示词库插件:集中管理提示词(增删改查、标签分类、导入导出、AI 优化),聊天快捷收录与调用。 DSH Prompt Library plugin: manage prompts (CRUD, tags, import/export, AI polish), quick capture & reuse in chat.
会话级自动上下文压缩插件:回合中每步前 + 回合结束检测上下文用量,超过会话阈值自动 compact,摘要注入上下文后自然继续(DeepSeek Harness / DSH)
Vertical prompt quick-jump rail for the DeepSeek Harness web conversation view
Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.
Injects one system-prompt section so a DeepSeek Harness agent thinks and replies in Chinese
Codex-style one-line disclosures for DeepSeek Harness reasoning and tool activity
Out-of-tree DSH bug-fix and compatibility plugin collection
将原作者 linshenkx 的 prompt-optimizer 移植到 DeepSeek Harness 的第三方插件
267 个即插即用的 AI 专家角色定义——从前端开发到区块链安全,从小红书运营到抖音策略(移植自 agency-agents-zh)
DeepSeek Harness 插件:让 agent 默认用中文思考与回复(移植自 superpowers-zh)
为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩,解决极简模式长任务无法持续工作的问题。
为 DeepSeek Harness 开发的「建议提示词」插件:单个 bundle 集成了宿主生成插件与 Web 输入框幽灵文字界面。每个 agent 回合完成后,通过一次有界的辅助 LLM 调用在会话日志中写入一条建议的下一条提示词;Web 端把它渲染为输入框内的幽灵占位文字,通过可配置的快捷键(默认 Tab)采纳进草稿。
Aggregate and selective DeepSeek Harness enhancements, including a standalone Windows launcher companion
Prompt Vault: 输入框上方的提示词库。📚 按钮展开面板,主题名 + 详情展开 + 一键填入输入框;支持新建/编辑/删除/搜索。数据持久化在 ~/.dsh/prompt-library.json。
编程陪伴 Node-host companion: opens a persistent, per-site popup window while agents work (minimizing + suspending its process tree to freeze playback while they wait), with multi-site profiles and an in-window return-to-chat button.
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.