AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate every call, settled by code the model never touches. Install the same decision workflow into your own agent: OpenClaw, Claude Code, Codex, or DeepSeek Harness.
Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace recall - and sliding-context awareness (compaction summaries in recall/search, compaction notice with one-click /compact fill).
Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
AI Inner OS 是一个面向 AI CLI 工具的插件，支持 Claude Code、Codex CLI、Cursor、OpenCode CLI。 它通过协议注入，让 AI 在正常完成任务的同时，额外输出一层可见的自由独白： ▎InnerOS：这仓库现在还像毛坯房，先把承重墙立起来再说。 不预设人格，不限制语气。AI 可以吐槽、得意、焦虑、冷笑、跳跃联想——或者什么都不说。独白是否出现，由 AI 自己决定。
Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliability infrastructure, not a sandbox.
Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command, reflex arcs fire with zero model calls, memory consolidates while idle, every failure is attributed before retry. Reproducible offline, MIT.
