by Hu9956

OpenAI Codex provider for DeepSeek Harness with device-code OAuth, Codex CLI import, token refresh, and a web settings panel.

by DamonBao

OpenAI Codex provider for DeepSeek Harness with ChatGPT OAuth, native settings, and account usage.

by 240xu

Unified web search provider for DSH

by tearslee

DeepSeek Harness (dsh) plugin: supervise a workbuddy2api gateway process and auto-register its models as an LLM provider

by tafcear

🌊 月汐 (kimi-tide) — DSH’s “Auto-select model for every step” plugin: Images are automatically routed to models with vision capabilities, coding tasks go to coding models, and casual chat or translation are handled by cost-effective models. You can view which model was selected each time and why via the panel · The per-step model router for DeepSeek Harness: any connected model, routed by your rules

by yuioi666

Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/Chinese UI.

by birat-chapagain

DeepSeek Harness plugin: use your OpenAI Codex (ChatGPT Plus/Pro) subscription through OAuth

by MoonlitDropOfBlood

Token consumption statistics plugin for dsh

by bobowsh

OpenCode Zen free model adapter for DeepSeek Harness (DSH) — DeepSeek V4 Flash Free, Nemotron 3 Ultra Free, MiMo V2.5 Free, Big Pickle

by YUEYUEXYS

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Di

by xiaobbl

Fix opencode go model list issue on dsh

by x2802490130-prog

# DSH Floating Balance / One-Click Exit Plugin

by CARVIN94

TRAE SOLO supplier plugin for dsh-router, ported from traework2api. Provides the traework supplier, a free SOLO chat channel, and reports single-account status to dsh-router core.

by katsos

LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged ov

by lovezi0

Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API ke

by PerryLink

Laya decision engine as a first-class Cordis service and model-visible tools for DeepSeek Harness.

by shuind

Compact Codex coding mode for DSH: light prompt guardrails against GPT over-explaining, with an editable prompt and native Codex-style tools.

by superfish058

DSH Model Proxy Plugin: proxy routing at the model granularity (Clash, etc.) + automatic retry on failure + multimodal model mirroring + per-model connection testing, model list synced with the official source, settings applied in real time.

by beijingwahw

DeepSeek Companion — The official companion plugin for DeepSeek Harness: conversation export / handoff summaries / cost optimization / global search + execution trace analysis, Prompt engineering workspace, multi-model arena, task orchestration, security and auditing (nine major modules, E–J, built on Cordis plugin architecture).

by MaRi23333

Unofficial Grok integration for eligible SuperGrok or X Premium subscriptions: grok-4.6 chat with main-loop web/X search, shared Grok CLI OAuth, configurable model visibility, and Imagine images saved

by BruceLanLan

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent

by eghrhegpe

dsh - A global panel in the UI sidebar that displays the credit usage of the SenseTime console

by elizax

Support setting the LLM proxy address

by qikairo7

How to Use Gemini with DSH — Turn Your Google AI Pro Subscription Into a Programming Model Pool: Multimodal / Frontend Generation / Image Generation / Multi-Account Scheduling