设计与三维建模

Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.

The WunderUI design system for coding agents: components, props, tokens, rules and skills.

Hand-picked design, motion, 3D and AI references, each with one idea worth stealing. Free, no key.

Turn a website URL into a launch video with voice-over. Edit by chat, export MP4.

Docs, decks, forms, apps you build and deploy, automations, and AI images, video and voice.

Transcription, subtitles, meeting transcripts, translation, audio conversion, and private memory.

Product design with Claude: phases, requirements, user stories, RICE, flows, dashboard, Jira.

Generate images, videos and audio across many AI models via one API, with quotes before you pay.

提供 YouCam API，用于 AI 图像和视频编辑与生成。

Gemini watches public YouTube videos and returns a timestamped brief or answers to your questions.

YouTube channel profiles and recent video inventories. Paid FlashData API.

Transcripts of every video of a YouTube channel or playlist; only new videos on a schedule.

Public YouTube comments and linked replies, Top/Newest sorting, likes and video metadata.

YouTube for AI agents: transcripts, comments, video stats, channel monitor, Shorts captions.

Deliver YouTube video, audio or clips to your cloud storage asynchronously. Paid FlashData API.

AI dubbing for YouTube videos: one cloned voice per speaker, synced SRT, YouTube audio tracks.

Parse a YouTube video id. URL discarded.

YouTube Creative Commons license-label metadata, not training authorization. Paid FlashData API.

Turn any YouTube video into text: transcript, title, channel, timestamps.

Real-time YouTube transcripts, comments, channels & video search MCP. Local npx or hosted OAuth.

YouTube transcripts for AI agents: text and timestamps for any video, channel or playlist.

Summarize YouTube videos or fetch transcripts. Pay-per-call via x402 (USDC on Base), no account.

YouTube transcripts/subtitles, comments + replies, Shorts and video/channel data.

1,413+ HD exercise videos with muscles and instructions, plus workout and program generation.

Prepare audio-guided tours: templates, travel programs, trips and participants for tour guides.

Fetch YouTube video transcripts individually or in bulk via get_transcript and get_bulk_transcripts.

Z-Image is an online interface for the Z-Image generation model with fast inference and prompt

Photos and a brief in, finished social-media designs out. First design free, no account.

Plan, write and price micro dramas and anime episodes. It does not make images, video or audio.

Make images, videos and speech: Nano Banana, GPT Image, Seedance, Kling, Wan and Gemini TTS.

面向 WCAG 合规、ARIA 实现和包容性设计的 Web 无障碍专家。适用于网站无障碍审计、落实 WCAG 2.1 AA/AAA 标准、使用屏幕阅读器测试或确保 ADA 合规，擅长语义化 HTML、键盘导航和辅助技术兼容性。

Run video actions on your actions.world datasets and track the runs.

在处理广告文案请求前使用，包括 RSA 标题、Meta、LinkedIn、TikTok 广告或批量变体。通过 ad_copy_validator.py 对每行检查平台字符限制和政策要求。广告系列策略与预算请使用 paid-ads。

用于自动化蛋白质测试与验证的云实验室平台，适用于蛋白质设计及结合测定、表达测试、热稳定性测量、酶活性测定或蛋白质序列优化等实验验证。也可通过 API 提交实验、跟踪状态、下载结果，使用 NetSolP、SoluProt、SolubleMPNN、ESM 等计算工具改善蛋白质表达或溶解性，并管理结合湿实验验证的蛋白质设计流程。

Turn a website into a short 9:16 video ad: script, cast, voice, shots, music. Asks before spending.

Generate, edit, and explore AI images. Flux, Imagen, LoRA identity swap, upscale, and more.

Drive web pages with the agent-browser CLI (Playwright engine) - the primary local browser driver. Connect over CDP to the shared browser-profile Chrome (the hands of vd:web-e2e), or run standalone with --profile isolation. Snapshot with @e refs, fill/click, video recording, network mocking, deterministic batch replay. Use when the user says "agent-browser", "record a video of the flow", "mock that API call in the browser", or asks for browser automation with built-in waiting.

Use when choosing between workflow vs agent patterns, structuring orchestrator/subagent pipelines, or writing a Claude Code agent template.

设计多代理系统（主管、群体、流水线）及工具 schema，并从运行日志中定位瓶颈。适用于代理分工或运行缓慢、成本较高的情况；不用于 Claude Code 工作流文件，后者请使用 workflow-builder。

设计和优化 AI 代理的动作空间、工具定义和观察格式，以提高完成率。适用于定义或调整代理工具集、动作空间、观察格式或代理执行环境。

设计和优化 AI 代理的动作空间、工具定义和观察格式，以提高完成率。适用于定义或调整代理工具集、动作空间、观察格式或代理执行环境。

重新设计指定的一个或多个代码仓库，使其便于智能体理解、控制和累积学习。当被要求让系统对智能体直观、符合智能体工效或具备智能体累积性时使用，随后修订其设计文档和计划。

AI-only ad scoring for Claude: score image, video or text ads on 13 dimensions before you spend.

Stage1 Inspector — local website capture, evidence views and design comparison

Design custom apparel from chat: AI art on tees and hoodies, then a checkout link to buy.

Turn a prompt, product link, or reference ad into a finished video ad via Creatify's Ad Agent.

CreationLoop is your Marketing Agent. Read the overview, offer, and FAQ; apply as a design partner.

Build zero-shot video models for object detection, and category and attribute classification.

Gency AI product image generation - MCP server for Claude, Codex, Cursor, VS Code

Discover Kavel's AI photo/video generators, get tuned prompts, and open the right tool on kavel.ai.