Clauday.

NVIDIA's NeMo team dropped Molt today and it shot to the top of Hugging Face papers with 647 upvotes. It's a PyTorch-native training framework for agentic reinforcement learning, a…

Anthropic published new guidance on July 24 for building with the Claude 5 generation, Opus 5 and Fable 5, and the headline number is blunt: they cut more than 80% of Claude Code's…

Harness Handbook picked up 163 upvotes on HuggingFace papers, out of Tencent Hunyuan. It goes after a problem nobody writes papers about because it sounds like a chore: when you wa…

PalmClaw hit 1.12k upvotes on HuggingFace papers, which is an absurd number for an agent framework paper. The idea is simple enough to explain in one line: stop making phone agents…

The harness-beats-prompting argument finally has clean numbers. From Prompts to Contracts, a paper posted July 9 by Joongho Ahn and Moonsoo Kim, takes a prototype enterprise LLM ag…

The same day OpenAI shipped ChatGPT Work, Meta Superintelligence Labs dropped Muse Spark 1.1 and opened the Meta Model API in public preview. This is not a chat model with tools ta…

xAI shipped Grok 4.5 to the public today, and Elon is calling it an Opus-class model. Look at the numbers and the framing is right. On SWE-Bench Pro it resolves a task in about 16,…

Meta took astryx, the design system it built and used internally for eight years, and open-sourced it. React and StyleX under the hood, 150-plus accessible components, theming, dar…

The vLLM Semantic Router team just published Micro-Agent, and the pitch is sneaky-clever. Instead of building a complicated multi-model orchestration in your application, you hide …

Anyone who's let a coding agent loose on a real feature knows the failure mode: it confidently builds the wrong thing, fast. OpenSpec, trending today at 57,000 stars, is a clean an…