GITHUB TOPIC
24projects include this topic
The "reasoning" topic on GitHub groups 24 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-better-reasoning-effort with 32 GitHub stars. dsh-better-reasoning-effort — Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card. 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
HaoyueQin
Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.
Aik358
Real-time chain-of-thought anchoring monitor & intervention plugin for DeepSeek Harness: three-band (spec/mixed/react) fingerprint detection, L1 hint / L2 reset / L3 restart interventions, liquid-glass web overlay + rheostat bar, standalone monitor process with JSONL experiment logs.
Chloride233
Real-time chain-of-thought trajectory profiling for DeepSeek Harness: live wording indicators, profile-family judgment, per-session measurement records
supersealwqas
DeepSeek Harness third-party API and custom model settings plugin: supports request headers, User-Agent, model list, image input and reasoning levels | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels
21hbguo
DSH "Big Fat Whale IQ detector": Thinking phrase detection stats · whole-session reasoning phrase hits/grouping/intelligence rating
54xkeee
DeepSeek Harness agent preset: fixes DeepSeek V4 Pro degradation (dumbing down) via RL first-request anchoring — bash+str_replace_editor bootstrap, resident plugin tools, per-turn format guard
DTSFO
Capability-aware reasoning controls and Fast model routing for DeepSeek Harness
HongzhongL
GrayPrint — dsh web plugin for live reasoning-style fingerprints. Scores paragraph openers against grayscale/current references and independently tracks Let me ↔ We need. 94.2% holdout.
lco117
DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.
Starfie1d1272
Minimal first-turn RL anchor for DeepSeek V4 on DeepSeek Harness Standard.
yumiao-dev
DSH 插件：直接在 DeepSeek Harness 对话里编辑任意 AI 消息的正文与思维链（thinking）。保留 AI 的聪明，让 AI 完全符合你的心意。🐛 修复选中删除联动清空问题。| DeepSeek Harness plugin to edit any assistant reply + reasoning/thinking chain. Make the AI output truly yours.
azazo1
DSH web plugin: cap expanded thinking blocks with a bounded scroll window.
dat-lequoc
Kiro provider for DeepSeek Harness with Builder ID login, live model discovery, and reasoning effort controls
bitterSmilezzz
DeepSeek Harness (DSH) 的增强模型选择器：单层菜单（搜索 + 分组）+ 底部内联推理强度（Effort）滑杆。
chiyulogg-commits
DeepSeek Harness reasoning summary sentence-by-sentence display version (one full sentence at a time)｜Sentence-by-sentence reasoning summary streaming for DeepSeek Harness — reasoning sentence-by-sentence summary reasoning sentence stream
luxueliu
Only ds can pick reasoning effort in DSH? Reasoning effort buttons for 20 common models are in place! Covers grok/Gemini / Kimi/glm……20 models are presets only, actual slots have no limit! Add your local gateway models freely! (reasoning effort tier plugin for non-ds gateway models + route-level llm-pi-ai patch)
walksls
跑了 20+ 批实验：这个 DSH 模式不会让模型更聪明，但更快更省。附带发现：它让模型少查资料、多靠猜。
William123666
Unofficial DeepSeek Harness plugin for Simplified-Chinese reasoning steering and opt-in translation.
zimodzh
DSH plugin that adds reasoning effort declarations to manually added OpenAI-compatible models / DSH plugin to declare reasoning efforts on hand-added OpenAI-compatible models.
emeryxu1-blip
Black-first Matrix hacker skin for DeepSeek Harness (DSH) Web — live session-powered code rain and readable provider reasoning.
Golopuer
When you use DeepSeek harness,you may hate that the big fish is always thinking in English,not Chinese(or the other language).Dot't worry,Deepseek has written an Plugin to translate it,but with qwen 3.5 0.8B's help......This Plugin will translate thinking without API.It is helped by deepseek V4 pro.
imdeniil
Палочки уровня размышлений для DeepSeek Harness: переключение глубины мышления одним кликом + меню моделей сразу списком. Effort bars: one-click reasoning level switching.
TOBYCAI
Idempotent model-tuning patch re-applied after DSH upgrades: DeepSeek reasoning widened to 7 levels, default model for workflow/ralph set to deepseek-v4-flash. Idempotent DSH model-tuning patch. | Platforms: macOS/Linux (Bash); Windows: Git Bash/WSL
YixuAnsensei
Claude Code plugin that unlocks full-power We need reasoning chains in DeepSeek Pro models: turn-aware DSH minimal simulation (official one-line persona + Bash/Edit pair on decision turns, full MCP tools + DSH persona on execution turns). Works with cc-haha.