Articoli Interessanti

LoRAX: Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

NextChat

The LLM Red Teaming Framework

Colette - ci ricorda molto Kotaemon

Memvid

VibeVoice: A Frontier Open-Source Text-to-Speech Model

[2502.12110] A-MEM: Agentic Memory for LLM Agents

[2504.19413] Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Apertus 70B: Truly Open - Swiss LLM by ETH, EPFL and CSCS

HumanLayer

PageIndex: Document Index for Reasoning-based RAG

Deploying DeepSeek on 96 H100 GPUs

Claude Code: A Highly Agentic Coding Assistant - DeepLearning.AI

DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning

[2508.15126] aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists

Alexander Kruel - Links for 2025-08-24

DSPy

AI Agents for Beginners - A Course

Turning Claude Code into my best design partner

How to build a coding agent

Tiledesk Design Studio

Build a Large Language Model (From Scratch)

Data Formulator: Create Rich Visualizations with AI

browser-use/web-ui

Casper Capital - 100 AI Tools You Can’t Ignore in 2025...

Parlant

CS294/194-196 Large Language Model Agents | CS 194/294-196 Large Language Model Agents

Show HN: Whispering – Open-source, local-first dictation you can trust

Fallinorg v1.0.0-beta

dokieli

paperetl

Automatically annotate papers using LLMs

My AI Had Already Fixed the Code Before I Saw It

Llama-Scan: Convert PDFs to Text W Local LLMs

Claudia – Desktop companion for Claude code

Show HN: Fallinorg - Offline Mac app that organizes files by meaning

Focalboard

Elysia: Agentic Framework Powered by Decision Trees

LangExtract

MCP-Use

+1 for "context engineering" over "prompt engineering"

The race for LLM cognitive core

[2507.07935] Working with AI: Measuring the Occupational Implications of Generative AI

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

Prava - Teaching GPT‑5 to use a computer

InstaVM - Secure Code Execution Platform

Sim

Litestar is worth a look

Jobs at Kaizen | Y Combinator

Launch HN: Lucidic (YC W25) – Debug, test, and evaluate AI agents in production

Introducing pay per crawl: Enabling content owners to charge AI crawlers for access

Agentic Design Patterns - Documenti Google

[2507.14447] Routine: A Structural Planning Framework for LLM Agent System in Enterprise

Qwen3-Coder: Agentic coding in the world

FutureHouse Platform

Voxtral | Mistral AI

Research Agent with Gemini 2.5 Pro and LlamaIndex  |  Gemini API  |  Google AI for Developers

AI Act, c'è il codice di condotta per un approccio responsabile e facilitato per le Pmi - Cyber Security 360

[2507.06398] Jolting Technologies: Superexponential Acceleration in AI Capabilities and Implications for AGI

MindsDB, an AI Data Solution - MindsDB

Backlog.md – Markdown-native Task Manager and Kanban visualizer for any Git repo

Opencode: AI coding agent, built for the terminal

The new skill in AI is not prompting, it's context engineering

SymbolicAI: A neuro-symbolic perspective on LLMs

Gemini for Google Workspace Prompting Guide 101

Judge Rules Training AI on Copyrighted Works Is Fair Use, Agentic Biology Evolves, and more...

MCP is eating the world—and it's here to stay

How Dataherald Makes Natural Language to SQL Easy "How Dataherald Makes Natural Language to SQL Easy" is already in English.

Field Notes From Shipping Real Code With Claude

Nice - my AI startup school talk is now up! Chapters: 0:00 Imo fair to say that software is changing quite fundamentally again

Nice - my AI startup school talk is now up!

Automated 73% of his remote job using basic automation tools, told his manager everything, and got a promotion

Building Effective AI Agents

How Anthropic Teams Use Claude Code

Snorting the AGI with Claude Code

Nanonets-OCR-s – OCR model that transforms documents into structured markdown

The Illusion of Thinking

Trends – Artificial Intelligence | BOND

Claude Code is My Computer | Peter Steinberger

[2505.24863] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

[2505.24864] ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

My AI Skeptic Friends Are All Nuts · The Fly Blog

Designing Pareto-optimal GenAI workflows with syftr

"BillionMail 📧 An Open-Source MailServer, NewsLetter, Email Marketing Solution for Smarter Campaigns"

Ask HN: What is the best LLM for consumer grade hardware?

[2411.06037] Sufficient Context: A New Lens on Retrieval Augmented Generation Systems

Show HN: Onlook – Open-source, visual-first Cursor for designers

Agent Development Kit (ADK)

Strands Agents

Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning

Introduction - IntelOwl Project Documentation

Show HN: My LLM CLI tool can run tools now, from Python code or plugins

[2505.03335v2] Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Codex’s Robot Dev Team, Grok's Fixation on South Africa, Saudi Arabia’s AI Power Play, and more...

[2502.00032v1] Querying Databases with Function Calling

Come Addestrare un LLM con i Tuoi Dati Personali: Guida Completa con LLaMA 3.2

AI Hedge Fund

Troy Hunt: Have I Been Pwned 2.0 is Now Live!

A Research Preview of Codex

[2505.06120] LLMs Get Lost In Multi-Turn Conversation