Havuz

Canvix — Free & open-source graphic design tool. A community-built Canva alternative with a drag-and-drop editor, templates, shapes, text, i

Open-source roguelike shooter for Android. Simple controls, no ads, no tracking, no internet permission. Free forever under GPLv3.

A browser-based whiteboard recording app with slides, backgrounds, camera overlay and teleprompter.

Generative UI for DeepSeek Harness — the agent writes TSX and the web UI compiles every frame as it streams, so a card renders while its JSX

Top 6 AI Paradigms Fighting for Survival in 2026

Open-source canvas for orchestrating Claude Code, Codex, and other CLI agents. Run agents in parallel, delegate tasks, and let AI build reus

🐹OFFICE ZOO · 班味剧场 — 让 9 名 AI 鼠人替你狠狠去下班味精神倍增!AI 自演的职场狼人杀模拟器,3 种玩法 / 真人 TTS / 可玩可学的劳动法闯关

BACKROOMS - No-Clip: roguelike de las Backrooms fiel al lore de la wiki. JavaScript vanilla + Canvas, sin dependencias. Codigo abierto no co

An organic glow that hugs the edge of your screen — zero-dependency Canvas 2D engine + React adapter

Local music analysis and deterministic video tooling for creators and coding agents.

Visual ZPL label designer for ZPL-compatible printers. Design, import, and export labels in your browser or as a local desktop app.

React components for real-time telemetry dashboards — robotics, aerospace, autonomous vehicles, industrial IoT. PFD, HSI, time-series, gauge

《以撒的结合》风格的俯视角肉鸽地牢网页游戏：12 层地牢 / 13 个 Boss / 55 件道具，零依赖零构建，全部美术由 Canvas 2D 代码绘制

The flowchart engine Alpine.js never had. Directive-driven node-based UIs with animation, layout, and collaboration.

Apple PaperKit for Expo/React Native

Scroll Video Website is a portable AI-agent skill that turns videos into smooth, scroll-controlled canvas experiences with optimized WebP fr

SafeLight is a modular image editing software that combines professional imaging tools with the customizability and modularity of modern IDE

Production-grade React Native ink engine with native Skia/Metal drawing and continuous canvas primitives.

Walkable worlds drawn entirely in text characters — a rain-lit cyberpunk city, a frontier town, the Moon and a castle town — in one HTML fil

A powerful Perler bead pattern editor —— 一个强大的拼豆图纸编辑器

MaddyPix — Compress, resize, convert, and enhance your images in your browser. 100% free, no uploads, 6 languages.

Tidy is an open-source agentic development environment for engineers and designers. Apache-2.0.

开源、可自托管的 AI 创作与模型管理平台：多模型对话、模型网关、无限画布、图片/视频/商品视觉、办公输出与运营后台（Vue 3 + NestJS）

Create, preview, and export Canvas motion graphics with Claude Code or Codex. Local-first and open source, with MP4, Lottie, and SVGA export

Motion graphics as a pure function of time — Canvas 2D scenes, headless-Chrome rendering with motion blur, ffmpeg, synthesized sound, and a

VGraph is a high-performance graph visualization and analysis engine for building interactive relation graphs, trees, DAGs, mind maps, and f

Solve text layout before you render. No DOM. No reflow. Real layout engine -- not just a measurer.

A browser canvas for coding agents: run Claude Code, OpenCode and Codex sessions side by side, watch what they touch, review every change.

🎨 Hand-drawn icons, animated illustrations & empty states for Jetpack Compose scenes, pure Canvas, zero image assets, fully theme-able.

agent-bridge

Isometric games made easy — an agentic game kit. 12 agent skills over 9 zero-dependency TypeScript packages. Type one sentence, get a playab

Stealth desktop AI assistant & interactive web showcase for CorvusX built with React 19, TypeScript, and Vite. Features a 60 FPS 3D particle

Cowork on a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and m

Animation drawn by code with Claude — no AI video: an engine, styles and skills that learn from every render, all in the open. PRs with new

An open canvas workspace for AI coding agents

Atmosphere is a client-side weather dashboard for live conditions, forecasts, air quality, astronomical data, local history, alerts, and off

麦麦餐厅-慧眼识人 | 麦当劳 2026 年 1024 程序员创意开发大赛参赛项目：基于麦当劳 MCP 真实餐品数据的出餐配餐与优惠推荐练习游戏（单文件 HTML，双击即玩）

A browser-first meme discovery and canvas editor with GIF support, Story export, sharing, and embeds.

DrawStamp Studio — browser-local online stamp maker & electronic seal editor. 在线生成、提取、编辑与导出电子印章，支持透明 PNG / SVG / JPEG。

✍️ True-native signature capture for React Native

麦当劳 MCP + 零依赖 Canvas 头像引擎：给你的项目快速配上麦当劳新品头像

Theme Designer Pro for Open WebUI: palettes, Canvas FX, gradients and custom CSS, with a live preset gallery and a Studio.

专为 ComfyUI 打造的开源无限画布 AI 创作工作台：纯前端直连自建与云端算力（首选推荐 LightCC 镜像开箱即用），工作流槽位驱动 UI，涵盖生图/全能参考视频/首尾帧，集成 Canvas Agent 与插件生态。Pure frontend infinite canv

救驾（救驾study / jiujia study）：给留学生的 Canvas / Moodle 学习手帐——盯 deadline、排本周该学什么、按状态给建议。Agent Skill，在 Claude Code、Codex 里说「帮我从 GitHub 安装救驾」就能装。

Claude Opus 5.5 directs and renders films in JavaScript: brief → sound (file, YouTube, generated, or AI voiceover) → director's treatment →

Анимация сборки из деталей LEGO в стиле инструкции и портреты из фото в духе LEGO Art. Нарисовано кодом на Canvas 2D, скилл для агентов

CellMotion：可编辑的文字、图标与媒体动效，导出 PNG/GIF/MP4，可交给 AI 前端复用 / Editable motion for type, icons and media

Free Vampire Survivors–style roguelite with Pokémon, in the browser. Unofficial fan game.

Tela — a fast, local-first, open-source design canvas for social & ad creatives. A brandable, self-hostable Figma/Canva alternative. No acco

Living 3D Procedural Jelly Avatar Engine, Web VTuber, Cute Anime TTS, AI Expression Creator Studio & Motion Exporter