Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, models.dev prices, context windows, live per-task token cost and a local-model filter. One-command install: dsh plugin add dsh-model-garden.
Writes live provider model lists into DSH settings. Composer rings show 5h/7d plan windows or metered balance for the current session model. / 把线上模型列表写进设置，输入框圆环显示当前会话的 5 小时/7 天窗口或按量剩余余额。
DeepSeek Harness web plugin: DeepSeek balance & platform usage monitoring inside the official Settings-Models-DeepSeek card, plus a live balance chip left of the model name in the composer tool row. Ported from DeepSeekMonitorWindows.
DeepSeek Harness (dsh) plugin: live NVIDIA GPU monitor in the web rightbar. NVML-first on Linux (nvidia-smi fallback). NVIDIA only! Not AMD/Intel/macOS. Multi-GPU util/VRAM/power/temp, processes, sparklines. Installable dsh.bundle.
A DeepSeek Harness plugin: per-segment Session cost in the composer statistics strip, priced from the harness model catalog (41 providers, ~1495 models).
