
Pastehex
Add drawings and annotations to HTML and Markdown pages with encryption.
pandrre · HN
I've built tldraw for HTML and Markdown pages (with encryption)
The full gallery
Tech stack
60 projects

Add drawings and annotations to HTML and Markdown pages with encryption.
pandrre · HN
I've built tldraw for HTML and Markdown pages (with encryption)

Create and edit multimodal content with AI using a conversational canvas interface.
BananaCanvas AI — 前沿的创意工作区,结合了基于对话的 AI 交互和无限画布,用于多模态内容创作。

Convert, edit, merge and compress PDF documents in your browser.
@IslandPDF · X

Input a project brief to generate alignment reports covering risks, questions, architecture and timeline.
@GroundedIQ · X
GroundedIQ exists to close the gap between what a client asks for and what actually gets built. That gap is where projects bleed — in change orders, blown timelines, and the slow erosion of trust between a consulting team and the people who hired them.

Store and share prompts, rules, and context that AI tools like Claude Code, Cursor, and ChatGPT can access via MCP.
@vibexp_io · X
Your plan is now code. Claude Code Dynamic Workflows fan out up to 1,000 subagents, 16 at once, each in its own context, verifying until the results converge. Built for big bug hunts, migrations and audits. Source:

Visual editor for configuring multi-agent LLM systems with local inference.
sascha10000 · HN
Multi-agent LLM editor with local inference via WebSockets

AI video editor that automatically cuts footage, adds captions, removes backgrounds, and exports to social platforms.
fredabila · HN
Vidmoat – a video editing pipeline any AI agent can operate

Manage academic conferences: submit and review papers, handle scheduling and registration.
@harryjwang · X
I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age

Krea2 Edit: identity-preserving AI image edits in-browser. Restage subjects, swap objects, keep likeness. No ComfyUI needed—try the live editor above now.
Krea2 Edit — 在浏览器中进行 AI 图片编辑,保留人物面部特征

Browser-based PDF tools for editing, converting, and managing documents.
@influnexe · X
thanks James. you can use all my tools for free here😄 :

Write and preview Markdown documents live in your browser with syntax highlighting.
@krishnakrmahto · X
Built Easy Markdown Editor — a reading-first Markdown editor where you edit the rendered document instead of raw Markdown.

Edit photos online with prompt-driven AI tools for retouching, cleanup, upscaling, and creative image generation.
AI Image Editor — 在线 AI 修图与图片生成工具,支持抠图、消除、放大、风格化和基于提示词的图片编辑,并提供 [ChatGPT Image 2](https://ai-image-editor.io/chatgpt-image-2) 免费体验