DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费，峰时正好是上班时间。

COS Glasses — self-hosted AI heads-up-display server for Even G2 smart glasses, powered by Claude Code, Codex, or Cursor Agent CLI

Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.

Real-time execution trace and cost intelligence for Claude Code

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

Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.

专门为 agent 打造的 agent 搜索工具，具备多语言搜索能力，覆盖中文/英文/学术/代码/购物/金融/新闻/百科。

Compact DeepSeek Harness desktop host with a native SwiftUI iPhone Remote source preview.

Pluggable DeepSeek-colored TUI for DeepSeek Harness

Audit and fix your Mac's security in one command. No agent, no signup, open source.

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.

Yet another WebUI for Nginx

🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.

深迹 DeepTrace — Your Agent, in numbers. DSH 插件：从会话事件日志生成日报/周报/月报/年报/自定义区间，确定性洞察与协作复盘，只读、不改写历史。

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

🐳 DeepSeek Harness Desktop

DSH - Dseam

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

DeepSeek Harness 独立社区插件商店：发现、安装并提交经过验证的插件、工具与扩展。 | Independent community plugin directory.

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.