Back to catalog

GITHUB TOPIC

local-llm

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

DSH PluginsPlugin

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.

Structure check pending
deepseek-harnessdsh-pluginllama-cpplocal-llm
Development toolsPlugin

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

Structure check pending
cordisdsh-pluginllama-cppllama-server
Models & MCPPlugin

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。

Structure check pending
ai-agentdeepseekllama-cppllm
Models & MCPPlugin

dsh-local-ai

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.

Structure check pending
cordisdeepseekdeepseek-harnessdsh
Models & MCPPlugin

dsh-llm-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.

Structure check pending
aideepseekdeepseek-harnessdeepseek-harness-plugin
InterfacePlugin

dsh-strata-sync

ethan741205

DSH plugin with a UI to synchronize model context and safe compaction budgets with Strata Server.

Structure check pending
deepseekdsh-pluginlocal-llmqwen
DSH PluginsPlugin

foreman-dsh

AllDurham

Expensive brain + cheap hands: cloud-orchestrator + local-worker lanes (delegate & read-only scout) for DeepSeek Harness | community Agent preset

Structure check pending
agent-presetdeepseek-harnessdsh-plugindsh-preset
Models & MCPPlugin

dsh-local-delegate

MythGreenLand

Delegate mechanical text work (translate/summarize/extract/classify) to a local cheap model endpoint, keeping large text out of the main model context.

Structure check pending
ai-agentsdelegationdsh-pluginlocal-llm
DSH PluginsPlugin

Local ollma-based model inference

Structure check pending
deepseek-harnessdshdsh-pluginlocal-llm
Agents & sessionsPlugin

fatfish-lab

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。

Structure check pending
agent-orchestrationai-agentb-plus-treebuffer-pool
InterfacePlugin

pi-dsh-tps

Ayshinko

Quiet DSH-style decode TPS for Pi — stable cumulative model generation speed with tool execution excluded

Structure check pending
deepseek-harnessllmlocal-llmpi
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

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

Structure check pending
deepseek-harnessdsh-pluginllama-cpplocal-llm
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Development toolsPlugin

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.

Structure check pending
agent-orchestrationai-agentcodexcodex-cli
DSH PluginsPlugin

Qwen/GenieX providers, reasoning parser, warmup and per-turn TTFT/TPS for DeepSeek Harness.

Structure check pending
cordis-plugindeepseek-harnessdshgeniex
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
DSH PluginsPlugin

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.

Structure check pending
chain-of-thoughtchinesedeepseek-harnessdsh-plugin
Models & MCPPlugin

dsh-llm-moe4all

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。

Structure check pending
deepseek-harnessdsh-pluginllm-inferencelocal-llm
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

dsh-local-trim

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.

Structure check pending
context-windowdeepseek-harnessdshdsh-plugin
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Development toolsPlugin

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

Structure check pending
ai-agentdeepseekllm-inferencelocal-llm
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Local LLM integration plugin for DeepSeek Harness

Structure check pending
deepseek-harnessdeepseek-harness-desktopdeepseek-harness-plugindeepseek-harness-plugins
Models & MCPPlugin

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Structure check pending
apple-siliconcoding-agentdeepseek-harnessdsh
Models & MCPPlugin

Per-tool-call safety review for DSH using an Ollama decision model

Structure check pending
ai-safetydeepseek-harnessdshdsh-plugin
Models & MCPPlugin

local_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)

Structure check pending
8gb-vramllama-cpplocal-llmninfer