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

Cost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Token insights.

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..

Usage billing dashboard plugin for DeepSeek Harness: sidebar cost metrics, real usage aggregation from session logs, current multi-provider pricing catalog

DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制

把本机 Wallpaper Engine 的壁纸搬进 DSH 网页界面：场景壁纸由内置 MIT 开源引擎 WebWallGL 实时 WebGL 渲染（粒子 / puppet 骨骼 / SceneScript / 音频反应 / 鼠标交互），失败自动降级内嵌 MP4 与场景静态帧；Web 壁纸严格沙箱 + WE API；iOS 风格液态玻璃 UI 高度自定义，遮挡暂停省电、ffmpeg 帧率上限转码、系统音频频谱与 Now Playing、自定义上传与自动轮播；设置存宿主端，对 agent 零 token 开销。Windows / macOS / Linux 三平台原生（同一个包、同一条命令）。

基本稳定可用 A context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).上下文压缩插件，兼顾小窗口(100k上下文足矣)省token(省5倍token)和超长会话(数月级别几十亿token单会话)。billion-context is all you need

安装即自带mattpocock/skills v1.2.3的25个工程与效率技能，无需手动装技能。300亿token打造。本插件在原始技能之上提供10倍的开发效率。主力支持GitHub issue；Markdown为预览版；GitLab暂不支持。

DSH 插件 · 注入式优化器 0.7（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳定性,尤其DeepSeek-V4.1-Flash,可有明显提升

dsh 插件 · 技能市场：一个页面管理本机所有 coding agent 的技能（Claude、ZCode、Codex 等十余个执行器），一键收编进 DSH 用户库供 skill 工具调用；内置 6600+ ntd 技能市场可浏览搜索安装，支持注入开销（≈token/字符）统计与排序、模型可见性治理与市场每日自动同步。

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry

Say goodbye to copy-pasting and DSH Token anxiety. Let ChatGPT on the web connect directly to your local project, code on its own, and hand complex tasks to DSH for sustained execution.

Core Goal Addon (Token Budget, Milestones, Git Snapshots & Retrospective Reports) for DeepSeek Harness

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.