llm-agent

Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Loops (auto-research) and more. #dsh

An Agent Skills skill for developing DeepSeek Harness (DSH) plugins（开发 DSH 插件的 Agent Skill）——插件/服务/事件/工具/LLM 适配器/打包安装的标准。Works with Claude Code, Codex, DSH, VS Code Copilot & any compatible agent.

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Session preservation.

The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.

Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution (prefercmd/memory as knowledge allow/deny lists), so repeated tasks start from proven commands and save tokens. Unified subagent routing and evolution: prefercmd/memory serve as knowledge allow/deny lists, saving tokens.

Source-grounded deep research, writing, and learning plugin for DeepSeek Harness (dsh): steerable checkpoints, mid-run steering, and citations verified against retrieved sources.

变更证明（ChangeProof）— DeepSeek Harness 插件：代码改动后确认改动的行真的被测试覆盖到

Real-time chain-of-thought trajectory profiling for DeepSeek Harness: live wording indicators, profile-family judgment, per-session measurement records

Minimal prompt x full PTC tools for DeepSeek Harness - aligned with the Project2 we/let's trajectory (Minimal 99/96). 已验证兼容 DeepSeek Harness v0.1.2-alpha.5。

Automated development pipeline plugin for DeepSeek Harness: requirement pool → LLM refine/design/plan/review → workspace-routed implementation → verify → merge → report

AiFP 记忆感知系统｜MCP 服务，一套记忆全 AI 共享。面向中文的 Agent 感知记忆，支持叙事链、语义纠错、感知链图扩散。兼容 DeepSeek‑Harness、Claude Code、Cursor、Codex等全部 MCP 客户端，数据完全本地存储。

Agent skills and a working template for building standalone DeepSeek Harness (DSH) plugins

Minimal first-turn RL anchor for DeepSeek V4 on DeepSeek Harness Standard.

Fleet OS · 舰队模式 — 生产级多 Agent 协同引擎：WS 黑板 + 事件溯源 + 盲评对抗 + 跨舰队接力 + 上下文压缩 + 多厂商负载均衡 + 自进化。36 模块，零运行时依赖，MCP 40 工具，48 项 e2e 全绿。

Cron scheduling for the DeepSeek Harness — bounded tasks with calendar & interval rules, delivered to live agents

该仓库暂未提供项目说明。

A real Red Alert 2 AI battlefield plugin for DeepSeek Harness with fog-safe control, live DSH Chat, and post-match learning.

LLM loop that reasons in a dense technical register — mechanical gates + adversarial judge + reverse-translation for humans. Self-upgrading. Standalone or as a DSH plugin.

ProactiveAgent × DeepSeek Harness 插件组：把主动记忆 + 主动建议接入 DSH（6 个 cordis 插件，引擎零重写）

该仓库暂未提供项目说明。

DSH 外置状态机插件 · 幻觉抑制守卫 + 证据背书验证 + 上下文经济 · Structured state machine for long-horizon autonomous agents

Feishu/Lark document design & layout skill for DeepSeek Harness (dsh) — management-readable, brand-consistent, evidence-traceable formatting for long-form docs. 飞书文档设计排版技能（DeepSeek Harness 技能插件）：管理层可扫描、品牌一致、证据可追溯的长文排版。

Feishu/Lark bid-proposal document generator skill for DeepSeek Harness (dsh) — structured pitch docs with cover, background, solution, pricing, team & cases. 飞书讲标方案文档生成器（DeepSeek Harness 技能插件）：封面/背景/需求/方案/报价/团队/案例等章节。

Feishu/Lark spreadsheet quotation generator skill for DeepSeek Harness (dsh) — auto cost, headcount, margin, payment milestones & ROI sheets. 飞书电子表格报价单生成器（DeepSeek Harness 技能插件），自动计算成本/人力/利润率/付款节点/ROI。

Evidence-driven Feishu/Lark document writing skill for DeepSeek Harness (dsh) — turn business material into verified, structured docs with conclusions, evidence & actions. 飞书文档证据化编写技能（DeepSeek Harness 技能插件）：从业务资料到可验证飞书成稿。