by GodD6366

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vis

by zhangjunjesse

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session

by jiay98528-dev

Writes live provider model lists into DSH settings. Composer rings show 5h/7d plan windows or metered balance for the current session model. / Write the live model list into settings; the composer ring shows the current session's 5h/7d plan windows or pay-as-you-go remaining balance.

by moon09300731

Auto-switches the agent to ultra-compressed caveman-style output during DeepSeek peak-pricing hours (Beijing 09:00–12:00 / 14:00–18:00, price x2) and shows a status badge plus transition toasts.

by Jesse-njx

dsh-polyglot — the model switch for DSH: generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek presets, automatic provider fallback on rate limits

by dfycaly98931680

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, on

by jiekesu967

Shows OpenCode Go subscription usage (rolling, weekly and monthly used and remaining percentage with reset times) in a floating panel anchored to the bottom-left of the session window.

by sequoiayunus-hue

Configure per-teammate model & reasoning effort for DeepSeek Harness native agent teams — settings UI, zero official-file modification. Visually configure model and reasoning effort levels for DSH native Team squad members.

by 54xkeee

Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)

by shenkonghui

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy aut

by GeekRicardo

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in pla

by faith1688

A real-time usage / cost / balance metering plugin built specifically for the DeepSeek API — view tokens, costs, and your actual balance right next to the chat input box.

by AIcivilization

Many model sources behind one OpenAI-compatible endpoint for DeepSeek Harness (dsh) and your tools: WorkBuddy, OpenCode Zen, Codex, Kimi… Multiple models merged into one OpenAI-compatible endpoint, usable directly by dsh and other software.

by FengHuoLinShan

DSH Plugin: Draggable API Balance/Quota Floating Card (Auto-Detection, Tiered Color Coding, and Real-Time Refresh for DeepSeek / Moonshot / Kimi For Coding)

by activeing123

DSH plugin bundle that mounts mcptoon as an MCP server: compresses MCP tool discovery from 71,929 to 581 tokens across 255 tools (-99.2%, measured).

by r600a-code

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM call

by dylan121322

Adaptive model routing: per-request complexity classification with automatic provider routing.

by shangjian2023

dsh plugin: 46-source daily RSS digest, LLM-edited, delivered via webhook (ServerChan/PushDeer/WxWork/TG/Bark/gotify)

by yingjunnan

DeepSeek API quota (balance) widget for the DSH web GUI: a floating bottom-right card showing remaining DeepSeek API balance.

by huyang2024

OpenAI-compatible HTTP surface for DeepSeek Harness (dsh): POST /v1/chat/completions, POST /v1/responses, GET /v1/models over the harness webServer + llm runtime

by BlackBearCC

A playable pixel companion plugin for DeepSeek Harness (DSH): platform-jumps over chat messages, WASD controllable, with a full nurture system fed by your agent's real token usage.

by 0xRabit

A free, 100% self-hosted DeepSeek Harness plugin that unifies your on-chain and CEX assets.

by ffyuuu

LongCat-2.0 LLM adapter: 1M context, binary thinking mode, tool calling, and streaming over the OpenAI-compatible endpoint.

by jiamuAi

DSH Token Usage Statistics Panel (Codex Style): Cross-instance Token consumption summary + Activity heatmap.