
v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
Stay updated with the latest developments in Artificial Intelligence

LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
Describe what you want in plain language. TRAE Work builds the page. BytePlus Pages puts it live. No coding, no server setup, just a shareable link.
Today, TRAE Work introduces Design Mode: a new way to create, iterate, and deliver your design work.
It's not just a new name. It reflects what TRAE has become: an AI workspace built for every professional, not just engineers. Two products, one mission, and a clearer home for everyone who works with AI.
Task does not wait for the moment you sit down at your desk. An idea hits while you're on the move. A task needs to be dispatched before the next meeting. A deliverable needs a quick review.
SOLO is now in free beta early access. An invite code is required to activate SOLO Desktop and Web.
TRAE launches new token-based pricing with four membership tiers from $3 to $100 monthly, starting February 24, 2026. A 14-day free Pro trial for new users is also available after this transition.
How to build and deploy AI software in a fast way with TRAE and Vercel
We've put together a guide on how to create, import, and use Agent Skills in TRAE.
How to build and deploy AI software in a fast way with TRAE and Vercel
We're introducing sandboxing and a multi-layer security system designed to reduce security risk while keeping AI productive.
We upgraded Cue with repository-level edit sequences that keep you in flow
We've put together a guide on how to create, import, and use Agent Skills in TRAE.
This is your year in review. Let's look back at what we created together.
This guide will get you started with using a coding agent like SOLO coder in just a few minutes., We'll show you how to use SOLO Coder for some common development tasks.
TRAE SOLO is the responsive coding agent we built for real-world software development.
How a lean team builds production features end-to-end with an AI engineer that “understands, executes, and delivers.”
We are introducing Max Mode, which is designed for deep coding with larger context windows and more tool calls.
Stop repeating yourself. In this article we dive into how to set up TRAE Rules that remember your preferences, keep your team aligned, and avoid the common mistakes that make AI ignore your instructions.
Showing 18 of 30 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news from Trae Blog
Join 15,000+ AI enthusiasts