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
Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.
Zero-touch runtime telemetry for DeepSeek Harness: every session writes its own report card (task/model/tools/failures/duration) into a human-readable journal. 纯观察者运行事实遥测。
Per-round reasoning_effort optimizer for DeepSeek Harness (dsh): auto-downgrades tool-call reasoning for simple tool chains, lifting back for heavy work. Cuts thinking time between tool calls.
Liquid-glass billing overlay for the DeepSeek Harness Web GUI: provider balances, session cost, daily spend and token buckets. DeepSeek-first and extensible.
DSH web plugin: see every session's conversation progress and token usage at a glance — all-windows overview, session analysis, cost estimation, and a token heatmap. 窗口统计插件：一屏看全所有会话的对话进度与 Token 消耗——全窗口总览、会话分析、成本估算、Token 热力图。
dsh-routines — scheduled agents for DSH: run a prompt on a cron, get the digest where you already are (file digests, chatnode delivery, unattended-safe)
Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, budget caps with threshold alerts and over-limit policies, carbon footprint estimation, per-model latency benchmarks, a Settings budget tab, and the /budget command
🌊 深海事务所 · Abyss — 把 DeepSeek Harness 的多 agent 运行画成一间看得见的事务所：委派谱系、每个 agent 的成本与失败归因、上下文水位、考勤时间线，历史案子可回放并一键导出 Markdown 复盘。A DeepSeek Harness plugin that turns an agent fleet into an office you can watch.
