Python

We look at zg (zvec-grep), the local-first search layer that Qwen Developers just open-sourced under Apache 2.0. We explain how it puts ripgrep, BM25, and vector search behind a single interface, so an agent can move from a plain-language description to an exact line span without switching tools. We cover the deliberately small MCP surface, the on-device embedding catalog, and the authorization gate that stands between local content and remote models.

Google Research has released TimesFM-3, a 330 million parameter time series foundation model that forecasts multiple related series in a single forward pass. Unlike every TimesFM checkpoint through 2.5, it is pretrained natively for multivariate forecasting, accepting multiple targets, past covariates, and past-future covariates with no task-specific fine-tuning. It takes the top average rank among pretrained foundation models on GIFT-Eval, fev-bench, and the TIME leaderboard. The weights, however, ship under a non-commercial, non-production license.

The OpenClaw Foundation has released v2026.8.1, which the project calls OpenClaw 2.0: 933 contributors, 569 first-timers, and more than 16,000 pull requests, roughly half of every PR ever merged into the repo. Setup now reuses existing subscriptions, API keys and local models. The rebuilt Control UI cut test-harness startup from about 1.6 seconds to 575 ms. Shared cloud sessions add real multiplayer, though the docs are explicit that they are not a security boundary.

Vercel has open-sourced vgpu, the WebGPU library it built to ship the shaders on vercel.com. It treats .wgsl files as importable TypeScript modules, runs the same shader in the browser, in headless Node.js via Dawn, and in a deterministic CI mock, and ships a fullscreen effect in 25 KB gzipped.

NVIDIA has released TensorRT Model Connect (TRTMC) in public preview, an Apache-2.0 project that takes a supported Hugging Face or local checkpoint to end-to-end TensorRT inference in two commands, with no intermediate ONNX export. The build emits a versioned .bundle artifact that runs through native C++ task APIs, so inference executes without PyTorch in the runtime path. NVIDIA's July 29, 2026 GB300 snapshot covers 105 release profiles across 76 model families.

NVIDIA releases NemotronLabs VoiceChat 11B, an open full-duplex speech-to-speech model with 448 ms latency and live tool calling.

NVIDIA Labs has open-sourced NOOA (NVIDIA Object-Oriented Agents), a model-agnostic Python framework for building AI agents. Agent development today is split across prompt templates,...

Meta Superintelligence Labs has released Muse Code, a terminal coding agent in beta, powered by the new Muse Spark 1.2 model. Muse Code plans changes, writes code, and validates results across large repositories. Async background agents stay active for the whole session instead of spawning per task. A local append-only event log makes the runtime replay-exact and restart-safe after a crash. Muse Spark 1.2 was co-trained with the harness and trained on long-horizon, repository-scale work.

CopilotKit has published the Channels SDK, an MIT licensed library that runs an existing AG-UI agent inside Slack and Microsoft Teams. Version 0.5.0 ships five platform adapters and a documented runtime contract. This breakdown covers the verified deployment paths, the baseline requirements, and the one dependency that is easy to miss

Genspark has open sourced GenOffice under the Apache License 2.0. It is an AI-native office suite for macOS and Windows, covering Docs, Sheets, Slides and PDF as five Electron apps over one shared engine layer. The notable engineering claim is a byte-preserving round trip: only edited paragraphs are regenerated as OOXML and spliced back into the original file, so untouched blocks keep their original bytes and layout survives in Word. Sheets pairs the open-source Univer core with an in-house Rust xlsx sidecar. AI calls route through a signed-in Genspark account and consume credits. The repository labels this an Alpha.

AMD released Instella-MoE-16B-A3B, a fully open Mixture-of-Experts language model trained from scratch on Instinct MI300X and MI325X GPUs. It holds 16B total parameters but activates only 2.8B per token, using Gated MLA and FarSkip-Collective. AMD published weights from every training stage, plus data mixtures, configs, and inference code.

Marktechpost AI has released Token Saver, an open-source MCP extension for Claude Desktop that uses local Hybrid RAG to slash PDF token consumption by up to 99% while ensuring absolute document privacy.

Liquid AI released two open-weight bidirectional encoders, LFM2.5-Encoder-230M and LFM2.5-Encoder-350M. Both carry an 8,192-token context and are built on the LFM2 hybrid backbone. The 350M ranks fourth of 14 models on a 17-task GLUE, SuperGLUE, and multilingual suite, behind only larger models. The 230M clears one 8K-token forward pass on CPU in about 28 seconds.

Microsoft AI has released MAI-Cyber-1-Flash, its first model built specifically for cyber defense. It is a 137B total, 5B active sparse MoE fine-tune of MAI-Code-1-Flash with a 256k context window. The model does not ship as a standalone endpoint — it runs inside MDASH, Microsoft's multi-model agentic scanning harness, where it handles up to 90% of tasks and pushes the system to 95.95% on CyberGym.

Developer Hayden Bleasel has released Blume, an open-source, MIT-licensed documentation framework. It reads a folder of Markdown or MDX and generates a hidden Astro project, shipping static, AI-ready docs with local search, 30+ MDX components, llms.txt, and a built-in MCP server.

Apple released container 1.0, an open-source Swift tool running Linux containers as lightweight virtual machines on Apple silicon.

Vercel has open-sourced eve, an Apache-2.0 agent framework now in public preview. An agent is a directory of files, with durable execution, sandboxes, approvals, connections, channels, and evals built in. Scaffold with npx eve@latest init and deploy unchanged via vercel deploy.

Databricks has open-sourced Omnigent, a meta-harness that sits above coding agents like Claude Code, Codex, and Pi. It adds composition, contextual policies, and live session sharing under one interface, on terminal, web, desktop, and mobile. The Apache 2.0 project is in alpha.

Describe a dataset in one sentence; Bigset's orchestrator and parallel sub-agents research the live web and return structured tables.

Nous Research releases Contrastive Neuron Attribution (CNA), a method that identifies and ablates sparse MLP neuron circuits to steer LLM behavior — no sparse autoencoder training, no weight modification, and no degradation of general capability benchmarks.

turbovec brings Google Research's TurboQuant algorithm to vector search, offering 16x compression and zero codebook training for RAG pipelines.

Vercel Labs has released Zero, an experimental systems programming language designed so AI agents can read, repair, and ship native programs without requiring human interpretation of compiler output. The language emits JSON diagnostics with stable codes and typed repair metadata, enforces capability-based I/O at compile time, and compiles to sub-10 KiB native binaries.

Poetiq's Meta-System automatically constructed and optimized an inference harness for LiveCodeBench Pro using only Gemini 3.1 Pro — no fine-tuning, no model internals. The same harness, applied without modification to GPT 5.5 High, Kimi K2.6, Gemini 3.0 Flash, and four other models, improved every one of them.

NVIDIA researchers have introduced Star Elastic, a post-training method that embeds multiple nested reasoning models — at 30B, 23B, and 12B parameter scales — inside a single checkpoint, eliminating the need for separate training runs or stored model weights per variant. Built on the Nemotron Elastic framework and applied to Nemotron Nano v3, the method trains all three variants in a single 160B-token run, achieving a 360× token reduction compared to pretraining each model from scratch. Beyond training efficiency, Star Elastic introduces elastic budget control — a novel inference scheme that uses a smaller submodel for the thinking phase and the full model for the final answer — delivering up to 16% higher accuracy and 1.9× lower latency compared to standard budget control, while nested FP8 and NVFP4 checkpoints bring the full model family within reach of RTX-class GPUs.

If you have spent time using AI coding agents — GitHub Copilot, Claude Code, Gemini CLI — you have probably run into this situation:...

Hugging Face has released ml-intern, an open-source AI agent designed to automate end-to-end post-training workflows for large language models (LLMs). Built on the company's...

NVIDIA researchers introduced ProRL AGENT, a scalable infrastructure designed for reinforcement learning (RL) training of multi-turn LLM agents. By adopting a 'Rollout-as-a-Service' philosophy, the...

Andrej Karpathy released autoresearch, a minimalist Python tool designed to enable AI agents to autonomously conduct machine learning experiments. The project is a stripped-down...

As the industry moves from simple Large Language Model (LLM) inference toward autonomous agentic systems, the challenge for devs have shifted. It is no...

While the tech folks obsesses over the latest Llama checkpoints, a much grittier battle is being fought in the basements of data centers. As...

NVIDIA has released VIBETENSOR, an open-source research system software stack for deep learning. VIBETENSOR is generated by LLM-powered coding agents under high-level human guidance. The...

What is Zero Padding Zero padding is a technique used in convolutional neural networks where additional pixels with a value of zero are added around...

Liquid AI has released LFM2.5-1.2B-Thinking, a 1.2 billion parameter reasoning model that runs fully on device and fits in about 900 MB on a...

Just months after releasing M2—a fast, low-cost model designed for agents and code—MiniMax has introduced an enhanced version: MiniMax M2.1. M2 already stood out for...

Mistral AI has introduced Devstral 2, a next generation coding model family for software engineering agents, together with Mistral Vibe CLI, an open source...

The new LiteRT NeuroPilot Accelerator from Google and MediaTek is a concrete step toward running real generative models on phones, laptops, and IoT hardware...

In this tutorial, we build an advanced multi-page interactive dashboard using Panel. Through each component of implementation, we explore how to generate synthetic data,...

In this tutorial, we explore the advanced capabilities of PyGWalker, a powerful tool for visual data analysis that integrates seamlessly with pandas. We begin...

How can we build AI systems that keep learning new information over time without forgetting what they learned before or retraining from scratch? Google...

Most LLM agents are tuned to maximize task success. They resolve GitHub issues or answer deep research queries, but they do not reason carefully...

Large language model serving often wastes GPU memory because engines pre-reserve large static KV cache regions per model, even when requests are bursty or...

Pokee AI has open sourced PokeeResearch-7B, a 7B parameter deep research agent that executes full research loops, decomposes a query, issues search and read...

In this tutorial, we explore the advanced capabilities of PyTest, one of the most powerful testing frameworks in Python. We build a complete mini-project...

How much compression ratio and throughput would you recover by training a format-aware graph compressor and shipping only a self-describing graph to a universal...

Do curated, tool-grounded demonstrations build stronger software agents than broad piles of generic instruction data? A team of researchers from Shanghai Jiao Tong...

oLLM is a lightweight Python library built on top of Huggingface Transformers and PyTorch and runs large-context Transformers on NVIDIA GPUs by aggressively offloading...

In many AI applications today, performance is a big deal. You may have noticed that while working with Large Language Models (LLMs), a lot...

Can safety keep up with real-time LLMs? Alibaba’s Qwen team thinks so, and it just shipped Qwen3Guard—a multilingual guardrail model family built to moderate...

Table of contentsWhat problem is it actually solving?Does the sample-efficiency claim hold beyond toy problems?How does the evolutionary loop look in practice?What are the...

IBM has released Granite-Docling-258M, an open-source (Apache-2.0) vision-language model designed specifically for end-to-end document conversion. The model targets layout-faithful extraction—tables, code, equations, lists, captions,...

In this tutorial, we walk through an advanced yet practical workflow using SpeechBrain. We start by generating our own clean speech samples with gTTS,...

Latvian language-tech firm Tilde has released TildeOpen LLM, an open-source foundational large language model (LLM) purpose-built for European languages, with a sharp focus on...

If you've ever tried to build a agentic RAG system that actually works well, you know the pain. You feed it some documents, cross...

We begin this tutorial to demonstrate how to harness TPOT to automate and optimize machine learning pipelines practically. By working directly in Google Colab,...

Experiment tracking is an essential part of modern machine learning workflows. Whether you're tweaking hyperparameters, monitoring training metrics, or collaborating with colleagues, it's crucial...

Visual reasoning tasks challenge artificial intelligence models to interpret and process visual information using both perception and logical reasoning. These tasks span a wide...

Introduction Amazon researchers have released Mitra, a cutting-edge foundation model purpose-built for tabular data. Unlike traditional approaches that tailor a bespoke model for every dataset, Mitra...

In this tutorial, we delve into Modin, a powerful drop-in replacement for Pandas that leverages parallel computing to speed up data workflows significantly. By...

Introduction: The Need for Dynamic AI Research Assistants Conversational AI has rapidly evolved beyond basic chatbot frameworks. However, most large language models (LLMs) still suffer...

The growing adoption of open-source large language models such as Llama has introduced new integration challenges for teams previously relying on proprietary systems like...

Data Scarcity in Generative Modeling Generative models traditionally rely on large, high-quality datasets to produce samples that replicate the underlying data distribution. However, in fields...

LangGraph Multi-Agent Swarm is a Python library designed to orchestrate multiple AI agents as a cohesive “swarm.” It builds on LangGraph, a framework for...

Meta AI has released Llama Prompt Ops, a Python package designed to streamline the process of adapting prompts for Llama models. This open-source tool...

In this comprehensive tutorial, we explore building an advanced, interactive dashboard with Taipy. Taipy is an innovative framework designed to create dynamic data-driven applications...

In a significant move to empower developers and teams working with large language models (LLMs), OpenAI has introduced the Evals API, a new toolset...

In today's information-rich digital landscape, navigating extensive web content can be overwhelming. Whether you're researching for a project, studying complex material, or trying to...

In this tutorial, we demonstrate how to evaluate the quality of LLM-generated responses using Atla's Python SDK, a powerful tool for automating evaluation workflows...

This tutorial will guide you through the process of using SQL databases with Python, focusing on MySQL as the database management system. You will...

Modern VLMs struggle with tasks requiring complex visual reasoning, where understanding an image alone is insufficient, and deeper interpretation is needed. While recent advancements...

In this tutorial, we will learn how to build an interactive health data monitoring tool using Hugging Face's transformer models, Google Colab, and ipywidgets....

The rapid growth of web content presents a challenge for efficiently extracting and summarizing relevant information. In this tutorial, we demonstrate how to leverage...

The advancement of artificial intelligence has ushered in an era where data volumes and computational requirements are growing at an impressive pace. AI training...

In this tutorial, we will do an in-depth, interactive exploration of NVIDIA's StyleGAN2‑ADA PyTorch model, showcasing its powerful capabilities for generating photorealistic images. Leveraging...

AI agents have become an integral part of modern industries, automating tasks and simulating complex systems. Despite their potential, managing multiple AI agents, especially...

Creating intelligent agents has traditionally been a complex task, often requiring significant technical expertise and time. Developers encounter challenges like integrating APIs, configuring environments,...

Operator learning is a transformative approach in scientific computing. It focuses on developing models that map functions to other functions, an essential aspect of...

Text-to-image generative models have transformed how AI interprets textual inputs to produce compelling visual outputs. These models are used across industries for applications like...

Developing web agents is a challenging area of AI research that has attracted significant attention in recent years. As the web becomes more dynamic...

Building large language model (LLM)-powered applications for real-world production scenarios is challenging. Developers often face issues such as inconsistent responses from models, difficulties in...

In the age of data-driven decision-making, access to high-quality and diverse datasets is crucial for training reliable machine learning models. However, acquiring such data...

Generative AI (Gen AI) is transforming the landscape of artificial intelligence, opening up new opportunities for creativity, problem-solving, and automation. Despite its potential, several...

One of the long-standing bottlenecks for researchers and data scientists is the inherent limitation of the tools they use for numerical computation. NumPy, the...

Hugging Face has introduced Observers, a cutting-edge tool that enhances transparency and understanding of generative AI interactions. This open-source Python SDK offers developers an...

Artificial intelligence systems often struggle with retaining meaningful context over extended interactions. This limitation poses challenges for applications such as chatbots and virtual assistants,...

In recent years, developing realistic and robust simulations of human-like agents has been a complex and recurring problem in the field of artificial intelligence...

Sentiment analysis, i.e., determining the emotional tone of a text, has become a crucial tool for researchers, developers, and businesses to comprehend social media...

Python is a high-level, flexible programming language that is well-known for its extensive ecosystem, ease of use, and readability. Python’s vast libraries and frameworks...

In recent years, formal software verification has gained prominence, especially in fields where software reliability is critical, such as aerospace engineering, finance, and healthcare....

The advent of artificial intelligence has catalyzed numerous sophisticated applications, and Podcastfy AI stands out as an advanced solution within the domain of audio...

Astral, a company renowned for its high-performance developer tools in the Python ecosystem, has recently released uv: Unified Python packaging, a comprehensive tool designed...

Professionals and enthusiasts in the finance industry need to have dependable tools for accessing and analyzing large amounts of data in order to track...

The development of autonomous agents capable of performing complex tasks across various environments has gained significant traction in artificial intelligence research. These agents are...

Time series data, representing observations recorded sequentially over time, permeate various aspects of nature and business, from weather patterns and heartbeats to stock prices...

Time series data is used globally across various domains, including finance, healthcare, and sensor networks. Identifying patterns and anomalies within this data is crucial...

DVC.ai has announced the release of DataChain, a revolutionary open-source Python library designed to handle and curate unstructured data at an unprecedented scale. By...

In computational chemistry, molecules are often represented as molecular graphs, which must be converted into multidimensional vectors for processing, particularly in machine learning applications....

In natural language processing, the advent of large language models (LLMs) has transformed how we interact with textual data. Among the tools available for...

With the growing complexity of large language models (LLMs), making them easily runnable on everyday hardware is a notable challenge. This need is apparent...

Python is a general-purpose programming language and is one of the most popular languages because of its versatility, ease of use, libraries, and active...

In the rapidly evolving world of technology and artificial intelligence, a new development has emerged that promises to impact the Python and AI communities...