208 results
Use DeepSeek web (chat.deepseek.com) as a free LLM provider in DSH — no API key needed. Plugin auto-launches a local gateway that drives a persistent browser; continuous chat, tool calls, model calibration, sub-agent concurrency.
DeepSeek 用量 / 成本 / 余额仪表盘 for DSH Web：输入框下方实时指标指示器 + 零依赖 SVG 用量可视化图表（含每轮成本视角、耗时叠加、异常标记、成本徽章、上下文压力条），token 数据来自官方 adapter 上报，成本按官方刊例价 + 用户覆盖 pricing.json 解析，余额来自官方 /user/balance 接口。
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Doubao Web by default (zero cost, no API key), Antigravity IDE quota (flash/pro), Gemini API, or Cockpit proxy — model-invokable vision tool, wrapper adapters, evidence memory, and a bilingual client panel.
GitHub Copilot adapter for the DeepSeek Harness LLM seam: OAuth device-flow sign-in, Copilot token exchange, and OpenAI-compatible chat completions against api.githubcopilot.com
Mobile-adaptive DSH web UI: on narrow screens the sidebar rail is hidden and the directory opens as an overlay drawer, so the conversation gets the full width.
Anime maid whale desktop pet for the DeepSeek Harness (dsh) Web UI: real-time LLM dialogues, 8 mood animations, satiety reserve system, persistent speech bubble, and mobile-adapted cupboard UI.
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
Finance and accounting workflows for DeepSeek Harness, adapted from Anthropic's Finance plugin.
OpenCode Zen provider adapter for DSH harness LLM seam
ECC (227k-star operator system) skills for DeepSeek Harness — progressive port of 274 curated single-file skills (agentic engineering, evaluation, testing, patterns, vertical domains, docs). Adapted from affaan-m/ECC (MIT)
Use AI agents from the DSH session UI.
DeepSeek-compatible adapter for the WeChat (chatapi.weixin.qq.com) gateway, with think-tag translation for the DeepSeek Harness LLM seam
GitHub workflow skills for DeepSeek Harness, adapted from OpenAI Codex GitHub workflow semantics.
Engineering workflow layer for DeepSeek Harness (dsh): a disciplined-engineer agent preset with five gated phases — requirements clarification, plan approval, TDD implementation, parallel subagent execution, and verified finishing. Skills adapted from the obra/superpowers workflow methodology.
Multi-agent collaboration suite for DeepSeek Harness: a user-configured specialist roster with on-demand dispatch (team_call / roundtable), model comparison, and a multimodal vision bridge — models come from the official provider flow, no bundled adapters.
DeepSeek Harness tools and Agent Skill adapter for Timeline Studio.
Runtime compatibility shim for dsh (DeepSeek Harness) cordis bundle plugins: decouples third-party plugins from real dsh internal service names, module paths, and RPC details via a version-aware adapter registry.
Route-aware Codex environment simulation for DeepSeek Harness, improving tool-call reliability for GPT and other Codex-adapted models
DSH 前端设计生成 Skill：把设计需求做成可直接打开的自包含 HTML/SVG 设计稿（海报/信息图/落地页/图表/组件稿）。Adapted from Anthropic canvas-design / web-artifacts-builder; zero runtime beyond markdown.
Hindsight memory manager for DeepSeek Harness: settings UI (intranet/extranet routes) with automatic check & install of the official @vectorize-io/hindsight-coding-agents DSH adapter
Cross-session usage & cost observatory for dsh — daily token charts, cache hit ring, 90d/1y heatmaps, model and project breakdowns, adaptive color themes and CSV export in the web UI
Web OAuth account surface for official DSH authorization flows
OneBot v11 HTTP and WebSocket adapter for DeepSeek Harness
Qoder CLI (qoder-agent-sdk) adapter for the DeepSeek Harness LLM seam