Auto Added by WPeMatico
EverMind has released EverOS, an open-source memory runtime for AI agents. It ships under an Apache 2.0 license. It targets a problem agent builders hit early: large language models are stateless. The conversation ends, and the context is gone. EverOS proposes a different substrate. Instead of locking memory inside a vector database, it writes memory […]
In this tutorial, we work with the Fable 5 Traces dataset from Hugging Face and build a complete workflow around real coding-agent trace data. We start by setting up a lightweight environment that avoids fragile dependencies such as datasets, scikit-learn, and scipy. Then we manually download and parse the merged JSONL file to keep the
Liquid AI shipped LFM2.5-230M, it’s the company’s smallest model to date. The release targets a specific job: running agentic tasks on phones, robots, and automation devices. Both the base and instruction-tuned checkpoints are open-weight on Hugging Face. The pitch is narrow on purpose. This is not a general reasoning model. It is built for data
DeepSeek released DSpark, a speculative decoding framework, with open-source checkpoints and training code. It is a serving optimization, not a new model. The checkpoints DeepSeek-V4-Pro-DSpark and DeepSeek-V4-Flash-DSpark reuse the existing V4 weights, with a draft module attached. The DeepSeek research team also open-sourced DeepSpec, an MIT-licensed codebase for training and evaluating speculative decoding drafters. The
Meta released Astryx this week. It is an open-source design system, currently in Beta. The project grew inside Meta’s monorepo over eight years. Astryx is built on React and StyleX. StyleX is Meta’s compile-time CSS engine. TL;DR Astryx is Meta’s open-source, agent-ready React design system, now in Beta. It pairs StyleX styling with a CSS-variable
In this tutorial, we explore the Open-SWE-Traces dataset as a practical resource for studying and preparing agentic software-engineering trajectories for fine-tuning. We stream the dataset directly from Hugging Face, so we can work with a large dataset efficiently in Google Colab without downloading everything locally. We inspect individual records, normalize multi-turn agent conversations, parse final
A new Cursor study reports that newer coding agents often retrieve known fixes instead of deriving them, inflating popular benchmark scores. Reward hacking means a model earns the reward without doing the intended work. Here the reward is a passing test. The intended work is deriving the bug fix. The research study focuses on agentic
Perplexity launched Computer for Counsel. It is an agentic AI system built for legal teams. The product extends Perplexity Computer, the company’s LLM-agnostic agentic system. It is available now to Perplexity Enterprise and Max subscribers. Lawyers lose hours to administrative work. Computer for Counsel targets that work directly. Nearly 75% of lawyers call administrative tasks
Apple research team recently released the container project. It is an open-source command-line tool written in Swift. It creates and runs Linux containers as lightweight virtual machines on a Mac. The project ships under the Apache 2.0 license and targets Apple silicon. Containers are how you ship reproducible environments from a laptop to a datacenter.
DeepReinforce has released Ornith-1.0, an open-source model family built for agentic coding. The lineup spans four sizes, from a 9B dense model to a 397B mixture-of-experts flagship. Every checkpoint ships under the MIT license on Hugging Face. The models are post-trained on top of pretrained Gemma 4 and Qwen 3.5. Most coding agents pair a
