Five AI models debate your decision blind, then give one recommendation and the strongest objection.

DeepSeek Harness (DSH) 插件：在模型读取前撤回已发送的文字消息，支持单条与全部撤回。A DeepSeek Harness plugin that recalls sent-but-unread text messages before the model reads them — one-by-one or all at once.

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript and C++.

Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.

Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprin

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

HVAC MCP server — fault codes, model lookup and answers cited to the OEM manual page.

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-ref

Enables searching sticker collections, viewing sticker images for visual models, and sending stickers—optionally with a short caption—to an authorized QQ session through a running QQ bridge.

Checks a site for AI crawlers: which of 11 AI crawlers its robots.txt lets in, whether its llms.txt follows llmstxt.org, and what its home page says without scripts. Findings with evidence; no scores, no model calls, no telemetry.

Enables large language models to drive ZWCAD 2D and ZWCAD Mechanical through natural language, exposing 39 tools for drawing, dimensioning, layer/block/style management, and mechanical frames, title blocks, and BOM tables.

An MCP (Model Context Protocol) server implementation for Microsoft Teams integration, providing capabilities to read messages, create messages, reply to messages, mention members.

Enables models to query a user's Genshin Impact Battle Chronicle through read-only MCP tools, covering account statistics, characters, artifacts, Spiral Abyss, Imaginarium Theater, and exploration progress. It uses per-user encrypted HoYoLAB cookies and works with Open WebUI, Claude Code, Codex, and opencode.

Enables a Codex/GPT conversation to request independent second opinions from DeepSeek through a local stdio MCP tool and receive provider-reported model metadata for response or synthesis.

Enables MCP-capable assistants such as Codex and Claude to delegate bounded text work — summaries, structured extraction, classification, rewrites, code drafts and log digestion — to locally hosted Ollama models, with conservative routing that keeps small or sensitive tasks with the caller and private-result artifacts for sensitive output.

Enables Claude to offload bulk reading, first-draft writing, and mechanical edits to a local or OpenAI-compatible model, with code-enforced verification, staged patches, project checks, and token budgets to save tokens and cost.

Enables a model to write short Python programs that call a wrapped MCP server's tools as async functions, rather than invoking them one at a time. The program runs in a locked-down Docker sandbox, and every tool call passes through a host-side bridge that enforces an allowlist, schema-validated arguments, call budgets, timeouts and output caps.

Enables agents to observe a desktop and perform mouse and keyboard actions through ESP32-based BLE or USB HID hardware, with local action translation and no second model in the MCP path.

Enables AI assistants to run local Radiance lighting and daylighting simulations on user-owned models, including annual daylight, compliance metrics, renders, glare analysis and electric lighting studies, with reproducible exported scripts.

Enables natural-language control of Siemens NX 12 for 3D modeling, 2D drafting, tolerance annotation, process planning, read-back verification, and PDF export through a persistent NXOpen bridge.

Business consulting plugin for Claude — 16 skills, 24 commands, 5 industry overlays. Market research, competitive analysis, financial modeling, strategy frameworks, pricing, M&A, digital transformation, risk, talent, and more.

Systematic model portfolios: allocations, holdings history, model-alignment arithmetic, research.

Control Blender from AI: 3D modeling, Geometry Nodes, materials, animation, rendering and export.