Jaaz is the world's first open-source multimodal canvas creative agent, serving as a Canva and Manus alternative that prioritizes privacy with local deployment. It features Magic Canvas for prompt-free creation where users build like LEGO through simple sketching and pointing, with AI instantly understanding and generating results. Supports one-prompt generation for complete images or videos using GPT-4o, Midjourney, VEO3, Kling, Seedance, and more.
Key features include infinite canvas for visual storyboarding with real-time collaboration, smart AI agent system that works with local (ComfyUI) and cloud models while maintaining multi-character coherence, flexible deployment (fully offline or hybrid with Ollama + APIs), built-in library for media and prompts, and enterprise-friendly Apache 2.0 licensing. Available on Windows and macOS with Python 3.12+ requirement.
Use Cases:
Jaaz.app Open source Canva AI alternative
The world's first open-source multimodal canvas creative agent This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.
📣 [New!] Enterprise Cloud “Full” Edition — Private/on-prem deployment & commercial licensing (Docker image or full source). Includes all jaaz.app online features. 30% OFF through Sep 15, 2025. Contact us → [email protected]
📣 [New!] 企业云端完整版 — 支持私有化部署与商业授权（Docker 镜像或源码交付），包含 jaaz.app 全量线上功能。限时 30% OFF，截止 2025-09-15。 了解/洽谈 → [email protected]
Download:https://github.com/11cafe/jaaz/releases
中文版|
新手指南
Magic Canva!
"Build" your ideas like playing with LEGO—paint directly, point with arrows, and the AI instantly understands and generates results.
Magic video!
https://github.com/user-attachments/assets/b7abf987-c65d-49b1-8178-82770873c583
Create Viral Shorts with a Single Sentence
Star us, and you will receive all release notifications from GitHub without any delay!
🎬 One-Prompt Image & Video Generation Turn one prompt into complete images or videos in seconds.
-Supports GPT-4o, Midjourney, VEO3, Kling,veo3,seedance etc.
-Auto-optimized prompts & multi-turn refinement
🧙 Magic Canvas&Magic Video Prompt-free creation — build like Lego.
-Simple sketching and free combination — AI instantly understands and generates.
-AI understands and generates instantly
-No prompt writing needed
-Describe steps simply on the video, and AI will generate following them.
🖼️ Infinite Canvas & Visual Storyboarding Plan scenes with an unlimited canvas
-Link layouts, manage media visually
-Real-time collaboration supported
🤖 Smart AI Agent System -Chat to insert objects, transfer styles, control logic
-Works with local (ComfyUI) & cloud models
Native graphical debugger for Windows x64 with custom RDI format and high-performance RAD Linker optimized for huge projects with gigabyte-sized debug info.
Cross-platform desktop assistant for Claude Code, Codex, and Gemini CLI with unified provider switching, MCP management, Skills system, and speed testing.
Unified AI inference SDK with custom NexaML engine providing Day-0 model support across NPU, GPU, and CPU with GGUF, MLX, and .nexa format compatibility.
One-click PC WeChat chat history export tool with permanent storage, comprehensive message type support, familiar interface, and multi-account incremental backup capabilities.
Open-source Nintendo 3DS emulator based on Citra supporting Windows, macOS, Linux, and Android with community translations, compatibility reporting, and multi-platform development.
SwiftUI macOS app that transforms MacBook notch into dynamic music control center with visualizer, calendar, file shelf with AirDrop, and complete HUD replacement.