11cafe/jaaz

The world's first open-source multimodal creative assistant This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 56 minutes ago
Added to GitGenius on September 10th, 2026
Created on June 1st, 2025
Open Issues & Pull Requests: 54 (+0)
GitHub issues: Enabled
Number of forks: 661
Total Stargazers: 6,636 (+0)
Total Subscribers: 35 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 37.7 hours
Mean response time: 91.5 days
90th percentile: 279.7 days
Tracked items: 47

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Only 0% of issues opened in the past year have been closed. Three people close 80% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 38
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 380 days
Stale 30+ days: 38
Stale 90+ days: 38

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Jaaz is an open-source multimodal creative assistant that provides a privacy-focused, locally-usable alternative to Canva and similar design platforms.

The tool addresses the need for creative work without reliance on proprietary cloud services or external dependencies. It operates as a canvas-based agent where users can sketch, paint, and point with arrows to communicate their intent directly to AI systems. Rather than writing detailed prompts, the interface lets users build designs like assembling LEGO blocks—the AI interprets visual gestures and generates results accordingly. The system supports image and video generation through multiple backends including GPT-4o, Midjourney, VEO3, and Kling, with automatic prompt optimization and multi-turn refinement capabilities.

Developers should choose this tool if they need creative generation features with full control over data and deployment. It suits projects requiring privacy guarantees, local execution, or integration into custom workflows where cloud-dependent solutions are unacceptable. The project offers both a web-based version and an enterprise edition supporting private or on-premises deployment with commercial licensing options. Unlike typical design tools that require manual prompt engineering, the gesture-based interface removes friction from the creative process, making it accessible to users who prefer visual communication over text.

The project maintains active development with regular feature additions including video generation capabilities and real-time collaboration support. The codebase is written in TypeScript and distributed through GitHub releases. Community engagement occurs through Discord, and the maintainers actively solicit feedback through GitHub stars as a notification mechanism for release updates.