dsh-agent-team-presets
bloodarea
Reusable Agent Team presets for DeepSeek Harness: a captain plus members with their own prompt, model, reasoning effort, and tools.
GITHUB TOPIC
7projects include this topic
The "agent-presets" topic on GitHub groups 7 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-agent-team-presets with 10 GitHub stars. dsh-agent-team-presets — Reusable Agent Team presets for DeepSeek Harness: a captain plus members with their own prompt, model, reasoning effort, and tools. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
{count} projects
Exact GitHub Topic match
bloodarea
Reusable Agent Team presets for DeepSeek Harness: a captain plus members with their own prompt, model, reasoning effort, and tools.
OrinVoss
DSH Math Modeling Team Plugin Pack: 2 role agent presets (modeling-coding / paper) for DeepSeek Harness, multi-folder Git collaboration + vision sub-agent; includes a full run on 2023 CUMCM-C. | DeepSeek Harness math modeling team plugin pack: 2 role Agent presets (modeling-coding + paper), multi-folder collaboration + vision sub-agent, with a full run-through of 2023 CUMCM problem C.
Meredith2328
Tuck the default four mode switches into the "New Session" button, making new session creation easier (Standard/PTC/Creative/Minimal, two-way sync with settings)
fan969690
DeepSeek Harness toolkit navigation: Web plugin set (dsh-web-plugins) / Windows desktop app (dsh-desktop-app) / AI knowledge base template (ai-knowledge-base)
fan969690
🧩 DSH module hub open-source framework: right-side modular desktop, grid layout for any module, custom sizes 1x1~2x6, long-press drag to reorder, open module protocol (register a plugin and it shows) + plugin community + Agent community (270 Chinese presets)
pearjelly
DSH-Heros · 深度荣耀 — pick Agent Presets as heroes, equip real tools and plugins, and level up through work.
Magica-Chen
DeepSeek Harness agent preset: Codex and Claude Code as delegation subagents, each at a read-only and full-access tier. Use either — or both in parallel — in one task.