Vercel Releases Eve: An Open Framework for AI Agents Where Each Agent Is a List of Force-Mapped Files

Vercel Releases Eve: An Open Framework for AI Agents Where Each Agent Is a List of Force-Mapped Files

Vercel is released the nightan open source framework for building, running, and scaling agents. The project is published as an npm package evelicensed under Apache-2.0. Building an agent should mean explaining what it does. It should not mean assembling all the plumbing that the agent needs to work on in production. eve is the framework … Read more

OpenAI Just Launched 3 Free AI Courses and Certifications

OpenAI Just Launched 3 Free AI Courses and Certifications

Having the right certification can make all the difference. But since there are so many, finding the right one is not easy. It is there OpenAI Academy enters. OpenAI, the company behind the ChatGPT models, has launched a learning platform through its OpenAI School that offers AI courses for up-and-coming professionals. These courses cover topics … Read more

MiniMax Sparse Attention (MSA): Two-Branch Block-Sparse Attention Trained on 109B-Parameter MoE with a 3T-Token Budget

MiniMax Sparse Attention (MSA): Two-Branch Block-Sparse Attention Trained on 109B-Parameter MoE with a 3T-Token Budget

MiniMax released MSA (MiniMax Sparse Attention), a sparse attention method built specifically on Grouped Query Attention (GQA). Target one bottleneck: the quadratic cost of softmax attention in the long context. The MiniMax research team tested it within a 109B-parameter Mixture-of-Experts model trained on native multimodal data. They also open sourced the inference kernel and shipped … Read more

Hermes Agent Adds Asynchronous Subagents, So the Delegated Task No Longer Blocks the Parent Dialog

Hermes Agent Adds Asynchronous Subagents, So the Delegated Task No Longer Blocks the Parent Dialog

Nous Research posted a change to Hermes Agent. Its agent tool can now use subagents equally. According to the announcement, the submitted function no longer blocks the parent conversation. Hermes Agent is an open source personal agent from Nous Research. A parent agent can spawn child agents, called subagents, to carry out work. So far, … Read more

What are Autoregressive Models? Time Series & AI Explained

What are Autoregressive Models? Time Series & AI Explained

Autoregressive models are one of the most important concepts in time series forecasting and sequence modeling. The term may sound technical at first, but the concept is surprisingly accurate. An autoregressive model predicts the next value by looking at previous values. That is the core concept. For example, tomorrow’s temperature may depend on the temperature … Read more

How to Build an Integration Pipeline with Docling Parse for Layout-Aware Document Intelligence

How to Build an Integration Pipeline with Docling Parse for Layout-Aware Document Intelligence

def create_demo_image(path): img = Image.new(“RGB”, (320, 180), “white”) draw = ImageDraw.Draw(img) draw.rectangle([20, 20, 300, 160], outline=”black”, width=3) draw.ellipse([55, 45, 145, 135], outline=”black”, width=4) draw.line([180, 140, 285, 45], fill=”black”, width=4) draw.text((45, 145), “Embedded bitmap image”, fill=”black”) img.save(path) create_demo_image(DEMO_IMAGE_PATH) def build_pdf(pdf_path): c = canvas.Canvas(str(pdf_path), pagesize=A4) width, height = A4 c.setFont(“Helvetica-Bold”, 20) c.drawString(60, height – 70, “Docling Parse … Read more

Sakana AI Sells AB-MCTS to Sakana Marlin, Business Agent Generating 100-Page Research Reports with Slides

Sakana AI Sells AB-MCTS to Sakana Marlin, Business Agent Generating 100-Page Research Reports with Slides

Tokyo-based Sakana AI shipped its first commercial product ‘Sakana Marlin’ this week. The Sakana team positions it as a Virtual CSO (Chief Strategic Officer). It is a B2B independent research agency built for businesses. Marlin doesn’t respond in seconds like a chatbot. You give it one research topic. It then runs automatically for up to … Read more

Z.ai Launches GLM-5.2 With 1M-Token Usable Context, Two Levels of Reasoning, and No Benchmarks at Launch

Z.ai Launches GLM-5.2 With 1M-Token Usable Context, Two Levels of Reasoning, and No Benchmarks at Launch

GLM-5.2 is the latest major language model from Z.ai, being the third major release in the GLM-5 line. It follows GLM-5 (February 11), GLM-5-Turbo (March 15), and GLM-5.1 (April 7). That makes four flagship-tier code releases in about four months. Userable 1M-Token Content Window The dominant specification of GLM-5.2 is the context window of 1,000,000 … Read more

Databricks Open-Sources Omnigent: A Meta-Harness That Connects, Controls, and Shares AI Agents on Claude Code, Codex, and Pi

Databricks Open-Sources Omnigent: A Meta-Harness That Connects, Controls, and Shares AI Agents on Claude Code, Codex, and Pi

Information bricks removed He is omnipotentopen source ‘meta-harness’ for AI agents. The project runs under the Apache 2.0 license. The Databricks AI team builds on Neon. A harness is a wrap model that turns into an agent. Claude Code, Codex, and Pi harnesses. Omnigent sits one level above them. Treats each harness as a flexible … Read more