Tag

OpenAI’s latest video-and-audio generation model with improved physics, realism, controllability, and synchronized dialogue and sound effects, available via the new Sora app.

Nano Banana (aka Gemini 2.5 Flash Image) is a state-of-the-art image generation and editing model from Google. It enables users to blend multiple images, maintain character consistency, perform targeted transformations via natural language, use world knowledge in image editing, and includes invisible SynthID watermarking to mark AI-generated or edited images.

nanochat is a full-stack, minimal codebase for training, fine-tuning, evaluating, and deploying a ChatGPT-like large language model (LLM) from scratch on a single 8xH100 GPU node for under $100.

SWE-agent is a system designed to empower language model (LM) agents to autonomously perform software engineering tasks. It features a custom agent-computer interface (ACI) that enhances the agent's ability to navigate repositories, create and edit code, and execute programs, achieving state-of-the-art results on the SWE-bench and HumanEvalFix benchmarks. [2, 5, 8]

12 Lessons to Get Started Building AI Agents

The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows. It is provider-agnostic, supporting the OpenAI Responses and Chat Completions APIs, as well as 100+ other LLMs via integrations like LiteLLM.

Agent Lightning is an open-source framework developed by Microsoft Research for optimizing and training AI agents using reinforcement learning (RL) and other techniques, supporting integration with any agent framework with minimal code changes.

The Claude Agent SDK for Python is an official library from Anthropic that enables developers to build, query, and interact with AI agents powered by Claude models, supporting tools, custom MCP servers, and hooks for advanced agentic workflows.

As a new-generation image creation model, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture. It supports multimodal inputs, reference images, and can produce high-definition images up to 4K with fast inference speed.

Learn how to use Cursor, an AI-powered code editor designed to make software development faster and more efficient.

An open-source, production-ready system for serving machine-learning models at scale.

Open-source deep-learning framework for building, training and deploying neural networks on GPUs and CPUs.