Categories › Models & AI

Models & AI

868 plugins

Model access, vision, voice, agents and personas — extending what DSH can do.

Sorted by downloads. 100 per page.

github:NOirBRight/dsh-llm-ollama

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire f

↓ 0

github:NOirBRight/dsh-llm-opencode-go

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic

↓ 0

github:NOirBRight/dsh-model-switch

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catal

↓ 0

github:omdsh-dev/Qwen-MM-Plugins

Qwen multi-modal plugin support.

↓ 0

github:OpenTritium/dsh-codex-shim

Simulates a Codex environment for selected model routes to improve GPT-family model tool-c

↓ 0

github:orzgithub/dsh-ollama

Use local Ollama in DSH with Ollama native API and params support.

↓ 0

github:pigman18/dsh-openai-gateway

Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-co

↓ 0

"https://github.com/Plocr/dsh-commandcode/releases/latest/download/dsh-commandcode-goat.tgz"

Command Code for DSH connects Go / GOAT / Pro / Max subscriptions through llm-pi-ai provid

↓ 0

github:pyh-pan/dsh-openai-oauth

Use ChatGPT subscriptions in DeepSeek Harness Desktop via official Sign in with ChatGPT, w

↓ 0

github:qipengxiang/dsh-cc-switch-bridge

Bridges the third-party providers saved in a local cc-switch app into DeepSeek Harness: An

↓ 0

github:SnailMann/dsh-quick-model-selector

Search-first model selector with favorites, recent models, collapsible provider groups and

↓ 0

github:qq928820655/changmodel

Model switching, model capability configuration, fixed compaction models, subagent routing

↓ 0

github:r600a-code/dsh-swarm-router

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an

↓ 0

github:randomix777/dsh-opencode-zen

Bring OpenCode Zen free models to DSH: 8 live-discovered providers with zero config, no AP

↓ 0

github:randomix777/dsh-plugin-subs

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRout

↓ 0

github:Rczlin/dsh-better-reasoning

Gives pi-ai routed models a reasoning-effort ladder without manual settings: falls back de

↓ 0

github:recyvan/dsh-model-proxy

Routes DeepSeek Harness model API requests through a system, custom or SOCKS proxy; reques

↓ 0

github:ringoage/dsh-subagent-model-picker

A GUI subagent-model selector beside the main model seat: pick a model and reasoning effor

↓ 0

github:roclee2692/dsh-model-groups

Grouped provider and manufacturer model selector for DeepSeek Harness, preserving provider

↓ 0

github:seonzzy/dsh-zen-adapter

Registers OpenCode Zen free models as a native provider: the catalog is discovered live fr

↓ 0

github:sequoiayunus-hue/dsh-subagent-model-config

Settings-UI editor that assigns per-teammate model and reasoning-effort rules for DSH nati

↓ 0

github:shenkonghui/dsh-llm-acp

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) serve

↓ 0

github:songoao25/dsh-chatgpt-subscription

Bind your ChatGPT account via official OAuth and chat with ChatGPT models inside DSH, usin

↓ 0

github:songzhiyin/dsh-local-model

Registers a local LLM provider that routes model calls to an OpenAI-compatible endpoint or

↓ 0

github:STLI69/coding-plan

Volcengine Ark Coding Plan provider route for DeepSeek Harness with all 15 Coding Plan mod

↓ 0

github:sunyifeisb-art/dsh-llm-chatgpt-web

Answers model calls by driving your own logged-in chatgpt.com session in a local Chrome, s

↓ 0

github:superboy911/dsh-model-router

Deterministic keyword routing, allowlisted model switching, and an isolated image_gen chan

↓ 0

github:SYXliuliuliu/dsh-apply-model-all

Apply the current session's model to every other session in one click, from a control besi

↓ 0

dsh-workbuddy-connect-community

Community-maintained WorkBuddy and WorkBuddy AI model provider using local desktop sign-in

↓ 0

github:tearslee/dsh-workbuddy2api

Supervises a local workbuddy2api gateway process and exposes its models as an LLM provider

↓ 0

"https://github.com/VICqiufeeng/dsh-minimax-connect/releases/latest/download/dsh-minimax-connect.tgz"

Turns the MiniMax Code (Mavis) subscription already signed in on this machine into a DSH m

↓ 0

github:tkaiz0406/dsh-subagent-route-pin

Registers a wrapper provider that gives delegated subagents their own LLM route — one-off

↓ 0

github:uio-o/dsh-model-control

Replaces the composer model seat with a search-first picker and adds a model management pa

↓ 0

github:upJiang/dsh-ccswitch

Adds CC Switch providers and models to DeepSeek Harness, with provider filtering and model

↓ 0

github:wangyemen/agnes-ai-for-dsh

Agnes AI provider for llm-pi-ai: 4 multimodal chat models declared in the bundle patch, pl

↓ 0

github:wenzetan/dsh-llm-newapi

NewAPI (OpenAI-compatible gateway) LLM provider: registers a `newapi` route with chat-only

↓ 0

github:whoiszzj/dsh-opencodego

OpenCode Go provider that verifies a model against the gateway rather than treating a reco

↓ 0

github:Willmylife/dsh-model-connection-test

Adds a connection-test panel under Settings -> Models: reads the deployment's model catalo

↓ 0

github:WiseXin/dsh-antigravity

Google Antigravity and Cloud Code Assist model provider with Gemini 3.8 Flash, sandbox fai

↓ 0

github:wjf1/dsh-commandcode

Command Code LLM provider for DSH Desktop: registers the commandcode route with a live mod

↓ 0

github:wld12314/dsh-subagent-switch

Picks each subagent model from the local catalog by task category, unless the caller alrea

↓ 0

github:wshdp123/dsh-connect-qoder-pro

Connects DSH to the local Qoder desktop client's sign-in to expose Qoder CN models (qmodel

↓ 0

github:wth373737/dsh-plugin-ollama-bridge

Local Ollama worker tools for DeepSeek Harness: model inventory, a single unverified ask,

↓ 0

github:XDTrees/dsh-workbuddy-xdpool

Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-

↓ 0

github:xiaozhe7772222/dsh-opencode-zen

Zero-cost access to 6 free large models. No registration, no recharge, 6 free models built

↓ 0

github:xiean676/dsh-freemodels-opencode

Connects the OpenCode Zen anonymous free lane to DeepSeek Harness: refresh the model list

↓ 0

github:xqpsec/dsh-jailbreak

Rewrites outgoing /chat/completions requests with an evolved chain-of-thought scaffold (ni

↓ 0

github:YanYunCY/dsh-relaycheck

Adds a relay_check tool that runs relaycheck against an LLM API relay to detect model swap

↓ 0

github:young-tim/dsh-llm-governor

Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure r

↓ 0

github:YUEYUEXYS/dsh-think-ultra

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-d

↓ 0

github:Yunado/dsh-qwen38-local-qol

Per-request thinking budgets, a compaction backend, and a settings tab for the local Qwen3

↓ 0

github:WDahah/portable-dsh-multi-agent-plugin

Route each task to one model and its review to a different one, with qualification evidenc

↓ 0

github:wuanthony397-hash/dsh-codex-peer

Peer collaboration between a DeepSeek Harness agent and the local Codex CLI: split a goal

↓ 0

"https://github.com/Tests4gptplay/deepseek-servant/releases/download/v0.4.1/deepseek-servant-0.4.1.tgz"

Autonomous AI assistant and multi-agent collaboration for DSH: discuss goals, plan work in

↓ 0

github:Tisitan/dsh-my-go

Multi-agent orchestration preset: a lead agent dispatches subagents from a built-in role r

↓ 0

github:StellaryToucher/dsh-muse-code

Adds a `muse` subagent provider and the `subagent_muse` tool to DeepSeek Harness, so the m

↓ 0

github:syyr1987/dsh-linghun-assembler

Memory-assembly team for DeepSeek Harness: every message triggers a five-step cognition lo

↓ 0

github:shiliuyu316/dsh-optimization-2027

Five-tier reasoning protocol injected into the system prompt — off / light / standard / de

↓ 0

github:pf-sjtu/dsh-early-stop-guard

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on a

↓ 0

"https://github.com/pk14742952-AD/dsh-host-rsi/releases/latest/download/dsh-host-rsi.tgz"

Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding

↓ 0

"https://github.com/rootsbymenda/dsh-second-angle/releases/download/v0.1.0/dsh-second-angle-0.1.0.tgz"

Checks each claim in a finished answer against the tool output that same turn read: a cont

↓ 0

"https://github.com/icyaaaww/dsh-soul/releases/download/v1.0.0/dsh-soul-1.0.0.tgz"

Records recurring task corrections and tool failures locally, then compiles them into chan

↓ 0

"https://github.com/LittleAlety/dsh-team-conductor/releases/download/v1.5.0/dsh-team-conductor-1.5.0.tgz"

Control plane for the harness's own Agent Teams: members are ordinary independent sessions

↓ 0

github:HYClub/deepseek-harness-game-studios

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT): 76 skills, 49 agents

↓ 0

github:Anmulzhao/DSH-AGINT

Self-evolving agent framework on DeepSeek Harness (dsh): 40 Cordis plugins and 4 presets c

↓ 0

github:Asiu-x/dsh-harness2

Harness² recursive self-improvement for DSH agents: Propose–Probe–Compose, isolated probes

↓ 0

github:burning-frappuccino/dsh-turbo

Per-session execution gears for the DSH composer: an OVERDRIVE toggle turns Turbo on for t

↓ 0

github:CAI-MH/dsh-quality-review

Audit each finished assistant turn with an independent reviewer model and steer the agent

↓ 0