Loading / 加载中
Thinkgap feed
Curated items are read from the processed items table and served as a bilingual feed.
9 items
AgentBrush is an MCP server that integrates image generation directly into coding editors like Claude Code, Cursor, and Windsurf. Users define their brand once, and the tool produces consistent product shots, icons, OG cards, and mascots without leaving the editor. Generated images are automatically saved into the project repository, streamlining asset creation for development teams.
Synopsule is a new app for Mac and iPhone that records and transcribes conversations locally using OpenAI's Whisper model. It automatically labels every speaker and only generates summaries when the user requests them. All processing stays on the device—no accounts required and no data is ever uploaded. The app is available on the App Store as a single $4.99 purchase covering both Mac and iPhone.
CakewordAI is a new mobile app that enables children to point their device's camera at any object, such as a cup or toy, and instantly learn its name in any language. The app uses on-device AI to segment the object into a sticker, pronounce its name in the target language, and save it to a personal Word Dex. It operates entirely offline with no accounts, no ads, and no data collection, emphasizing privacy. The launch on Product Hunt targets parents seeking a safe, multilingual learning tool for young children.
Kimi AI assistant, listed on Product Hunt, has been updated to version K2.6. The update introduces real-time web search across over 100 websites, analysis of up to 50 files (PDF, DOC, PPT, images), an AI slides and website maker, state-of-the-art coding capabilities, and enhanced image understanding beyond basic text extraction. The features aim to support everyday productivity tasks with multimodal and code-specific improvements.
PixelForge converts a single photo into a recognizable RPG character that walks, producing a 4-direction sprite pack. The output includes a 4x4 sprite sheet with 16 transparent PNG frames and walk GIFs. Assets are ready for Godot, Unity, or the web. The tool is a one-time purchase of $5 with no account or subscription required. Generation uses AI, with finishing touches applied through code.
Google has released Gemini 3.5 Live Translate, an audio model designed specifically for near real-time speech-to-speech translation. The feature is now available within Google AI Studio, Google Translate, and Google Meet. It produces natural-sounding translated speech with low latency, aiming to enable seamless multilingual conversations in live meetings and direct translations without a text intermediary.