Tag
32 articles
SpaceXAI has open-sourced the Grok Build framework, a Rust-based system powering its coding CLI, including an agent loop, tool layer, and TUI. The underlying Grok 4.5 model remains closed-source.
Researchers have developed an autonomous data science agent using DeepAnalyze-8B that operates efficiently on limited GPU resources like T4 instances, demonstrating advanced data analysis capabilities through sandboxed code execution.
OpenAI launches ChatGPT Work, an advanced AI agent designed to perform actions across apps and files, moving beyond simple conversation to active task completion.
Anthropic has expanded access to its Claude Cowork AI agent to mobile and web platforms, enabling users to interact with the AI assistant across devices. The move blurs the line between Chat and Cowork modes, enhancing AI integration into everyday workflows.
Developers can now build a nanobot-style AI agent in Google Colab with full control over tools, memory, and model interactions.
Learn how NVIDIA's SpatialClaw AI can solve 3D spatial reasoning problems by writing Python code, without needing prior training.
Vercel has open-sourced Eve, an Apache-2.0 licensed AI agent framework where each agent is structured as a directory of files mapped to specific capabilities. Developers can scaffold and deploy agents using simple commands, leveraging Vercel's infrastructure.
Moonshot AI launches Kimi Work, a local desktop agent for macOS and Windows, powered by a 300-sub-agent swarm and running on Kimi K2.6.
Learn to build a simplified AI agent that interprets natural language requests and performs tasks like scheduling appointments or sending emails, similar to Meta's Hatch product.
An AI agent discovered 21 previously unknown vulnerabilities in FFmpeg, a widely used open-source multimedia framework. This development highlights the power of AI in automated cybersecurity and vulnerability detection.
Microsoft releases a tutorial for running its Fara browser-use agent in Google Colab using a mock OpenAI-compatible endpoint, enabling developers to experiment with autonomous web browsing.
Google's new Gemini Spark AI agent demonstrates impressive capabilities but raises concerns about privacy risks and financial costs. The technology's 24/7 operation and data access requirements create significant tradeoffs for users.
