AIAny
AI Client2026
GitHub

dsh-workbuddy-connect

Exposes models available in the WorkBuddy / WorkBuddy AI desktop apps to DeepSeek Harness with zero configuration. Reuses local app login and balances, shows separate domestic/international model groups, supports image inputs and inference-tier selection; intended for personal research use.

Introduction

Most local LLM desktop apps lock models and credentials inside their own runtime; this plugin flips that by surfacing WorkBuddy's locally available models inside DeepSeek Harness without extra tokens or account setup. That makes it trivial to route conversations in DSH to models bundled inside the WorkBuddy desktop app while keeping each app's account and credits isolated.

What Sets It Apart
  • Zero-config mounting: automatically discovers and exposes models that the logged-in WorkBuddy / WorkBuddy AI desktop app already provides, so users don't need to copy tokens or reconfigure providers. This reduces friction when you want to experiment with a model that only ships inside a vendor desktop app.
  • Account-and-balance preservation: each edition (domestic “WorkBuddy” and international “WorkBuddy AI”) appears as its own model group and retains the app's login state and credit balance. So billing and quotas remain tied to the original app rather than DSH credentials.
  • UX-aware features: displays available inference tiers when declared by WorkBuddy, offers manual detection for undocumented tiers (costs small requests), and shows per-account balance inline in the composer for quick decision-making while prompting.
  • Multimodal support where available: many connected models accept pasted or dragged images (e.g., GLM-5.3-Flash, DeepSeek-V4 series), while purely text models explicitly indicate lack of image support.
Who It's For & Tradeoffs

Great fit if you: want to use models shipped inside the WorkBuddy desktop apps from within DeepSeek Harness; prefer not to manage extra API keys; or need per-account balance visibility while switching models. Also useful when a required model is only distributed inside a vendor desktop client.

Look elsewhere if you: require a production-grade, server-side inference service or centralized API keys for multi-user deployment (the plugin is designed to reuse a single machine's desktop app state and is targeted at personal/research use). Be aware that the project is community-maintained, explicitly unaffiliated with WorkBuddy/Tencent/DeepSeek, and usage may impact your WorkBuddy account balance or service terms.

Information

  • Websitegithub.com
  • Authorscorrinehu
  • Published date2026/08/17

Categories

More Items

GitHub
AI Agent2026

Runs persistent, self-hosted AI teammates that retain conversation, memory, routines and a sandboxed browser/shell. Supports bring-your-own models, local or remote sandbox providers, voice, team computers and integrations for auditable, controllable agent workflows.

GitHub
AI Client2024

Unifies visual creator tools, reusable Skills, and a Codex-powered Agent to handle video translation, image/video generation, voiceovers, and editing in one local multimodal workspace. Desktop and web clients share a synchronized state machine and keep data local by default.

GitHub
AI Client2025

Private, local-first desktop assistant for voice and text conversations that runs models on your hardware. Uses local model servers (Ollama or OpenAI-compatible endpoints), offers personal memory, dictation, TTS/STT, MCP integrations and automatic redaction; free for personal use.