MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It consolidates many everyday writing, structured-data, and SEO tasks into one lightweight HTML-based web app, with a free hosted version and GPL-3.0 license.
Who it is for
- Content writers and editors
- SEO practitioners and digital marketers
- Web developers handling JSON and metadata
- AI-assisted content creators
Use cases
- Checking word count in article drafts
- Cleaning up compressed or poorly formatted JSON
- Generating meta tags for webpage SEO
- Analyzing keyword density in text samples
Strengths
- 31+ utilities in one toolkit
- Works directly in a modern browser with no separate runtime
- Available both as hosted build and local repository
- Free and open source under GPL-3.0
Considerations
- Configuration is per-utility through the interface, not global
- Local use may require a static web server for consistent behavior
- Troubleshooting is limited to refresh, input validation, and issue reports; no extensive documentation yet
README quick start
Getting Started
Description
Azhai is a browser-based toolkit with 31+ free AI, text, and SEO utilities for word counts, JSON cleanup, metadata generation, keyword evaluation, and other content workflows in 2026.
Related repositories
Similar projects matched by category, topics, and programming language.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.