What Is vLLM? The Open Source AI Model Server, Explained
vLLM is free, open source software that serves open AI models to many users at once. What PagedAttention does, how it differs from Ollama, and who should use it.

Open-source AI models and tools, with production comparisons and release news. Recent posts compare open-source text-to-image models like FLUX.1 and Stable Diffusion 3.5, open code models like Qwen2.5-Coder, and cover Reflection AI's Apache 2.0 Beam 1.0 release.
vLLM is free, open source software that serves open AI models to many users at once. What PagedAttention does, how it differs from Ollama, and who should use it.

Downloadable weights help, but the OSI definition of open source AI also asks for data information and training code. Say open weights, and check the license.

NVIDIA gave OpenShell, its open source runtime that sandboxes AI agents and enforces what they can touch, to the CNCF as a Sandbox project at KubeCon.

Atuin Threads syncs Claude Code and Codex sessions across machines. HN fans liked it, security-minded developers balked, and many had built their own.

Google released A2UI 1.0, a stable open protocol that lets AI agents answer with forms, cards and charts drawn by each app's own components, not text.

Browser Use 1.0 deletes 80% of the open source library: its agent now writes Python run straight on Chrome via CDP, and defaults move to Browser Use Cloud.

Yogurt is a free, open-source AI meeting notes app that keeps audio and transcripts on your computer. What Hacker News and X said about privacy and rivals.

Alibaba merged its Qoder agent harness into open-source Qwen Code 1.0 Preview. What changed, how to install it, what it costs, and the preview caveats.

AWS Emulator runs AWS APIs on your laptop for tests and coding agents. AWS says autonomous agents wrote all of its code, with no human review.

Olmo is Ai2's family of fully open AI models: weights, training data, code and checkpoints are public. Here are the models, the licenses, and who should use it.

llama.cpp is a free, open source program that runs AI language models on your own computer. Learn what it does, GGUF files, quantization, and how to try it.

CHIMERA is an MIT-licensed browser synth that speaks, sings and beatboxes from a simulated airway, not samples. An AI agent tunes it against real voices.

Asahi Linux is moving from MIT to the GPL after its unreleased code was copied and rewritten with LLMs. Omarchy fans, critics and GPL backers react.

DeepSeek released an MIT-licensed prototype of an always-on coding agent: one Router talks to people, isolated Workers do the jobs. Its docs warn of risks.

Deepgram is acquiring Daily, maker of the open-source Pipecat voice agent framework. Pipecat stays BSD-licensed, and an independent foundation is planned.

AIKON is an open source app that lets old Nokia Java phones chat with Claude, ChatGPT, Gemini and Grok. Features, credit prices and the security trade-off.

Brilliant Labs' Halo is a pair of $399 open-source AI glasses with a low-res sensor instead of a photo camera, plus Noa, an AI companion with plans from free to $39.99 a month.

Anthropic, OpenAI, Hugging Face and Alibaba gave Agent Skills, Open Responses, OpenEnv and OpenSandbox to the Agentic AI Foundation, the home of MCP.

DeepSeek open-sourced DeepInfer, the Apache 2.0 inference engine behind DeepSeek-V4.1-Flash, for NVIDIA SM100 and Huawei Ascend 950. What it includes, what it leaves out, and what DeepSeek's claim of 155 trillion tokens a day and $38 per GPU-hour does and does not show.

Asymptote Labs raised a $5.5M seed for Beacon, an MIT-licensed tool that records sessions from Claude Code, Cursor, Codex and 20+ other agents and turns reviewed lessons into reusable skills. How it works, what Pro costs, and what to check first.