Back to catalog

GITHUB TOPIC

reasoning-effort

24projects include this topic

The "reasoning-effort" topic on GitHub groups 24 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-codex-effort-slider with 150 GitHub stars. dsh-codex-effort-slider — Codex 风格的推理等级滑条(DeepSeek Harness 插件):可拖动连续滑条 + 高档位渐变星尘特效. 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

Development toolsPlugin

Codex 风格的推理等级滑条(DeepSeek Harness 插件):可拖动连续滑条 + 高档位渐变星尘特效

Structure check pending
aiai-agentscodexdeepseek
DSH PluginsPlugin

Codex-style reasoning-effort slider for DSH, plus a big fat fish running slider. Codex-style model and reasoning-effort slider for DeepSeek Harness

Structure check pending
deepseekdeepseek-harnessdsh-pluginreasoning-effort
Agents & sessionsPlugin

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.

Structure check pending
automationdeepseekdeepseek-harnessdsh-plugin
DSH PluginsPlugin

DeepSeek Harness 自己的 fast 模式:按步骤自适应思考档位 + 按档位批量并行工具调用,零依赖;只使用当前路由真正声明过的档位,官方 API 与自建网关都支持。

Structure check pending
agentdeepseekdeepseek-harnessdsh
DSH PluginsPlugin

Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (wire spellings) + request modalities (vision) for OpenAI-compatible providers. Settings section, zero runtime harness deps, no YAML.

Structure check pending
ai-providersdeepseekdeepseek-harnessdsh-plugin
Models & MCPPlugin

DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

Structure check pending
ai-agentdeepseek-harnessdeepseek-harness-plugindsh
Models & MCPPlugin

Add Low, Medium, High and other reasoning levels to DeepSeek Harness third-party APIs, with model selection for each subagent call | Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Structure check pending
deepseek-harnessdsh-pluginmodel-provideropenai-compatible
Models & MCPPlugin

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

Structure check pending
deepseek-harnessdshdsh-pluginmodel-provider
Models & MCPPlugin

Unofficial DSH Desktop provider extension: composer provider/account/model controls with per-account subscription quota

Structure check pending
chatgptcodexdeepseek-harnessdsh
Agents & sessionsPlugin

🧠 DSH plugin for custom model reasoning effort management & persistent preference memory | Custom model reasoning effort management & cross-session memory for DeepSeek Harness

Structure check pending
cordisdeepseekdeepseek-harnessdsh
DSH PluginsPlugin

DSH (DeepSeek Harness) plugin: unified default reasoning level (thinking effort) for all models — per-model defaults with capability probing, live call statistics, one-command install via dsh plugin

Structure check pending
deepseekdeepseek-harnessdshdsh-plugin
Agents & sessionsPlugin

dsh-context-pilot

Shuffle-1992

DSH 上下文智能压缩 + 智能思考:每轮注入用量、模型自主决定压缩并自动续跑;可选让模型按任务难度自主调整思考强度档位

Structure check pending
context-compressioncontext-managementcordis-plugindeepseek
InterfacePlugin

dsh-toolkit

Vast-Unhurried

DeepSeek Harness utility toolbox: notes, API balance and cost, delete sessions, third-party model reasoning level, conversation node navigation bar, light neumorphic skin

Structure check pending
banlancedeepseek-harnessdshdsh-plugin
DSH PluginsPlugin

dsh-effort

AI-Galaxy-GPU

DeepSeek Harness plugin: choose the model's reasoning effort for a session in the Web GUI; the Starlight reasoning selector switches Off / Default / High / Max with one click.

Structure check pending
deepseekdeepseek-harnessdsh-pluginreasoning-effort
Models & MCPPlugin

DSH plugin: context-aware per-step reasoning-effort routing — classify → escalate → hysteresis → capability clamp; Auto mask in the native selector; default effort fill + wire mapping for custom llm-pi-ai models. AI-authored (kimi-k3), produced by @neo805. No Issues/PRs; forks welcome (MIT).

Structure check pending
cordisdeepseek-harnessdshdsh-plugin
InterfacePlugin

Model-aware reasoning effort slider for DeepSeek Harness, with a Claude-inspired WebGL energy field, native themes, and a live demo.

Structure check pending
ai-uiclaude-inspireddeepseek-harnessdsh-plugin
Agents & sessionsPlugin

Claude-style Ultra mode for DSH: the top reasoning effort plus Claude's standing multi-agent orchestration.

Structure check pending
claude-codedeepseek-harnessdshdsh-plugin
Files & dataPlugin

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

Structure check pending
deepseek-harnessdshdsh-plugininput-modalities
Development toolsPlugin

Codex-style reasoning effort slider for DeepSeek-Harness that adapts to each model's own number of thinking levels.

Structure check pending
codexdeepseek-harnessdshdsh-plugins
Development toolsPlugin

dsh-orquestrator

frederico-kluser

DeepSeek Harness plugin: pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.

Structure check pending
agent-skillsai-agentscoding-agentcordis
Models & MCPPlugin

Automatically add reasoning-level controls to compatible DeepSeek Harness provider models

Structure check pending
deepseek-harnessdsh-pluginopenai-compatiblereasoning-effort
Models & MCPPlugin

Flash-only reasoning-effort routing for DeepSeek Harness, setting the DeepSeek flash model reasoning effort per step. The model never changes; effort max is opt-in.

Structure check pending
deepseek-harnessdshdsh-pluginreasoning-effort
InterfacePlugin

dsh-model-caps

raomaiping-hash

DSH plugin: per-model reasoning-effort levels and input modalities for custom llm-pi-ai providers — fields the official Models page does not expose. Cordis plugin, install via dsh plugin --profile web add github:raomaiping-hash/dsh-model-caps

Structure check pending
deepseek-harnessdshmodel-configreasoning-effort
DSH PluginsPlugin

DSH Web plugin: per-model reasoning-effort configuration and selection — settings page + slider embedded in the model picker.

Structure check pending
deepseek-harnessdsh-pluginreasoning-effort