Back to News
Hazy ResearchFebruary 19, 2026

ThunderKittens 2.0

Open Source
Agentic AI
Infrastructure

Explore ThunderKittens 2.0

Visit the official website to learn more and get started

### TL;DR

ThunderKittens 2.0 is an open-source CUDA-embedded domain-specific language (DSL) developed by Hazy Research to facilitate the creation of high-performance GPU kernels. This release focuses on optimizing existing kernels and introducing new features to enhance computational efficiency.

Key Insights & Metrics

Pricing
Free
Cost structure
Version
2.0
Current release version
Hardware
NVIDIA GPUs with support for MXFP8/NVFP4; CUDA-capable GPUs; 8GB RAM
Compute requirements
Category
Open Source
Licensing model
Region
United States
Primary region

Key Features

  • MXFP8/NVFP4 support
  • CLC scheduling
  • Tensor memory controllability
  • Parallel Global Layout (PGL)
  • Simplified build structure

Related Releases

AIO Sandbox

AIO Sandbox is an integrated environment designed for AI agents, combining a browser, terminal, filesystem, VSCode, Jupyter, and MCP Server into a single Docker container. This unified setup allows seamless development and execution of AI agents without the need for multiple services.

Agent InfraOct 29
Open

Mistral Forge

Mistral Forge is a system designed for enterprises to build frontier-grade AI models grounded in their proprietary knowledge. It enables organizations to train models on internal data, ensuring alignment with unique operations and compliance requirements.

Mistral AI
Open

Entropic

Entropic is a desktop companion application designed to monitor and manage AI coding agents such as Claude Code, OpenAI Codex, and Google Gemini. Developed by Dominant Strategies, it provides real-time tracking of project activities, session diagnostics, prompt history, and maintenance tools, offering a unified interface for developers to oversee their AI-assisted coding workflows.

Dominant Strategies
Open

MiroThinker

MiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.

MiroMindAI
Open

Discussion

0
Upvotes
0
Downvotes
0 reviews

Sign in to leave a review

Reviews

No reviews yet. Be the first to review!

🚀 Join the AI dev community — follow us everywhere

© 2026 MARKTECHPOST AI MEDIA INC. All rights reserved.Terms & ConditionsPrivacy Policy
Beta Mode