llama.cpp now has an official website: https://t.co/vztdUpdBWL
Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications.
While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine).
We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.
@ErickSky Te entiendo y por eso nunca dije que lo convertiría en mi modelo principal, pero si es de gran ayuda como agente secundario, siendo gratuito claro que te ayuda a ahorrar tokens. En un mundo de tantos modelos es una locura creer que con uno solo vas a poder hacer todo.
@kevincodex I don't know if @gitlawb will implement something similar for #OpenClaude in the future, but I think collaborating with this project would be a good idea.
Introducing a 100% free coding agent with DeepSeek v4 Pro
Choose any model, all free:
- DeepSeek v4 Pro/Flash
- Kimi K2.6
- MiniMax M2.7
npm i -g freebuff
Gemini 3.5 Flash understands complex topics and diagrams for your specific needs to visualize the results in a way that’s perfect for you.
Watch Gemini take an advanced math paper, explore it visually, and generate the elements that matter most.
@GeminiApp ❤️ I love your updates!
The page tha created to learn how programming languages work is incredible 🚀.
It even includes an AI assistant to answer questions on the spot 🤖💬
This is how coding should be taught! 🧠✨
#Gemini#AI#Programming#LearnToCode
https://t.co/TJFoeP5GpW
🚨 ¡La nueva actualización de Gemini es una LOCURA! 📷Ahora puedes crear apps, presentaciones y audio directamente desde el mismo chat. El razonamiento y la generación de aplicaciones están a OTRO NIVEL. 📷 @GeminiApp#Gemini
https://t.co/b1lSrwgsKd
🚨 ¡La nueva actualización de Gemini es una LOCURA! 📷Ahora puedes crear apps, presentaciones y audio directamente desde el mismo chat. El razonamiento y la generación de aplicaciones están a OTRO NIVEL. 📷 @GeminiApp#Gemini
https://t.co/b1lSrwgsKd
Terminal Threads are live in Zed v1.3.5!
You can now run claude, amp, pi, or any terminal-based workflow as a managed thread in the Threads Sidebar, right next to your other agent threads.
@kevincodex@gitlawb@XiaomiMiMo The best part is that it automatically generated API storage from the browser's local storage without my request. @XiaomiMiMo security approach is undoubtedly excellent.