Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘：实时看会话压力、按模型估算花费。预算和余额点一下就能改，每天每月用了多少都有记录。
A Claude Code skill that turns a document or a topic into a designed visual explainer. 52 block forms, an enforced word budget, and guards that fail the build.
Local Markdown wiki as long-term memory for DeepSeek Harness — RRF-fused retrieval (keyword + wikilink graph + temporal), token-budget injection, auto-capture. Ported from llmwiki.
Cross-session persistent cost ledger for DeepSeek Harness: logs every LLM token usage to SQLite and exposes record/query/budget tools. Built-in DeepSeek pricing, overridable via config.
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
Safe third-party web fetch for DSH — delegates page crawling to user-configured services with no direct URL access (no SSRF), API keys in the managed credentials store, per-session budget, and an auto-managed local web scraping service stack.
Local-life toolkit for DeepSeek Harness agents: budget planning, bill splitting, unit-price and discount math, common unit conversions (incl. jin/li/chi, C/F), and trip/outing checklists
DeepSeek Harness file-safety guardrail that limits AI coding-agent file edits per turn and prevents too many file changes, with call and UTF-8 byte budgets. 限制 DSH Agent 每轮修改文件数量。
