- Projects
- Web Elements
- Codespaces
Create New
Create Challenge
Create Web Elements
Create Project
Create Mobile Components
Create Codespace
Browse
Projects
All
Web Elements
All
Mobile Components
All
Challenges
All
Published
Views
Appreciations
Followers
Published
Views
Appreciations
Followers

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!

Python tool for converting files and office documents to Markdown.
Innovative and detail-oriented software engineer with 5+ years of experience in developing scalable web and mobile applications. Skilled in languages like Python, JavaScript, and C++, with a strong foundation in data structures and algorithms. Passionate about clean code, system design, and continuous learning. Proven track record of delivering high-impact projects in Agile environments. Committed to building tech that solves real-world problems efficiently.
Innovative and detail-oriented software engineer with 5+ years of experience in developing scalable web and mobile applications. Skilled in languages like Python, JavaScript, and C++, with a strong foundation in data structures and algorithms. Passionate about clean code, system design, and continuous learning. Proven track record of delivering high-impact projects in Agile environments. Committed to building tech that solves real-world problems efficiently.