dsh-qwen38-local-qol
Yunado
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B/Flash-Next): per-request thinking budgets, a compaction backend that stops burning the output cap on thinking, and a settings tab.
GITHUB TOPIC
34projects include this topic
The "local-llm" topic on GitHub groups 34 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-qwen38-local-qol with 25 GitHub stars. dsh-qwen38-local-qol — DeepSeek Harness QoL plugin for the local Qwen3. 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
Yunado
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B/Flash-Next): per-request thinking budgets, a compaction backend that stops burning the output cap on thinking, and a settings tab.
Adds local LLM capability to DSH: one-click start/stop of local llama.cpp models in Settings → Plugins (dual-slot x dual-modal x dual-preset), configure inside the card, one-command install, auto-register, ready to use | Enable local large model capabilities for DSH: One-click start/stop for local llama.cpp models (dual‑slot × dual‑modal × dual‑preset) right in Settings → Plugins; configure within the card, install with a single command, automatically register, and ready to use
liuda1999
DeepSeek 超级个人工作台:项目管理与文件、文档管理,可在会话中自由调用、索引文档,随时召唤/切换智能体角色。
PerryLink
Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.
1035041186
dsh-llm-ollama is a community plugin built for DeepSeek Harness (dsh) that lets Harness connect to a local Ollama service via the Ollama native protocol (/api/chat). Plug and play: no changes to any official dsh files; after installation an Ollama page automatically appears in Settings, and the provider's models are offered in the session model selector.
ethan741205
DSH plugin with a UI to synchronize model context and safe compaction budgets with Strata Server.
AllDurham
Expensive brain + cheap hands: cloud-orchestrator + local-worker lanes (delegate & read-only scout) for DeepSeek Harness | community Agent preset
MythGreenLand
Delegate mechanical text work (translate/summarize/extract/classify) to a local cheap model endpoint, keeping large text out of the main model context.
nnbw-liu
Local ollma-based model inference
Uneadlight
一个跑在 DSH 里的 AI 编码智能体:手搓 4KB 页 B+树、Socket RPC、多智能体编排,151 项测试全绿,本地小模型 + 云端协同。
Ayshinko
Quiet DSH-style decode TPS for Pi — stable cumulative model generation speed with tool execution excluded
bachkoo102
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
Castillo82728
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
ClearLeaf13
把本地 llama.cpp 管理器里的模型接入 DeepSeek Harness — bring local llama.cpp manager models into DeepSeek Harness
DenizKaya23
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
ewal96623
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
fabio7729
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
fengyu-12
把 OpenAI Codex CLI 接入 DeepSeek Harness 作为第二引擎:异步工单 / 双向互审 / 终端↔网页共享会话桥 / 文件任务板 · Plug Codex CLI into DeepSeek Harness as a second agent.
Fuxfantx
Qwen/GenieX providers, reasoning parser, warmup and per-turn TTFT/TPS for DeepSeek Harness.
Giulio2229
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
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.
Headmaster218
MoE4All local inference plugin for DeepSeek Harness: engine management, model discovery and downloads. / DSH 本地推理插件:引擎管理、模型发现与下载。
jenok9283
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
Korkmaz1974
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
Leonlee114514
Give small local models a light harness in DeepSeek Harness: per-provider tool mask, prompt-section trimming, light instruction injection, tool-schema slimming. Cloud providers untouched.
lpatel887
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
mehmetmorel
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
Phamt11163
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
regdiliKUN
把 Strata 推理引擎和 DeepSeek Harness Agent 拼成开箱可用的本地 AI 工作台|Local AI workbench: Strata 125B MoE inference + dsh agent, with one-click setup, folder upload, prompt enhancement and VRAM diagnostics
rkowalczyk2782
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
wertyBSd
Local LLM integration plugin for DeepSeek Harness
yamada6184
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
Yersi88
Per-tool-call safety review for DSH using an Ollama decision model
zkkk9555
8GB 显存跑 27B 三元模型的完整存档:NInfer KVMem 引擎参数、上下文取舍实测、llama.cpp 262K 路线、控制台与 DSH 接入(不含权重与引擎)