Articoli Interessanti

Omnara — The open-source alternative to Claude Managed Agents

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Claude Code from Source: Architecture, patterns & internals of Anthropic's AI coding agent

Munder Difflin — Agent harness to run an office of your clones

Why your local LLM feels dumber than it is

Error by AI scribe during medical appointment leaves patient devastated

Everyone is building LLM routers, we deprecated ours

Kimi K3 Architecture Notes

GitHub - block/buzz: A hive mind communication platform

Nativ — Run AI locally on your Mac

GitHub - tamnd/kage: Shadow any website for offline viewing, with the JavaScript stripped…

GitHub - boyter/cs: codespelunker - CLI code search tool that understands code structure…

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

GitHub - roboflow/supervision: We write your reusable computer vision tools. 💜

How LLMs Actually Work | 0xkato

Introducing Gemma 4 12B

GitHub - chiennv2000/orthrus: Fast, lossless LLM inference via dual-view diffusion…

Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver

GitHub - lahfir/agent-desktop: Native desktop automation CLI for AI agents. Control any application through OS accessibility trees

GitHub - openai/privacy-filter: OpenAI Privacy Filter

Introducing Unsloth Studio | Unsloth Documentation

Bring Your Agent to Teams | Teams SDK

Emotion Concepts and their Function in a Large Language Model

Nicholas Carlini - Black-hat LLMs | [un]prompted 2026 - YouTube

Qwen

Introducing Claude Opus 4.7 Anthropic

GitHub - arman-bd/guppylm: A ~9M parameter LLM that talks like a small fish.

Embarrassingly Simple Self-Distillation Improves Code Generation

Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs

PrismML — Concentrating intelligence

GitHub - microsoft/VibeVoice: Open-Source Frontier Voice AI

GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automatically

GitHub - Pinperepette/snakebite: Detect malicious PyPI packages using heuristic analysis and LLM-powered filtering to uncover credent

GitHub - 666ghj/MiroFish: A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

Introducing Mistral Small 4 | Mistral AI

GitHub - andrewyng/context-hub

Coding my Handwriting — Amy Goodchild

GitHub - jundot/omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the mac

My chief of SEO, Claude Cowork

Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned

GitHub - NousResearch/hermes-agent: The agent that grows with you

GitHub - bytedance/deer-flow: An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, m

spent the entire day testing Qwopus (Claude 4

GitHub - z-lab/paroquant: [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

I packaged up the 'autoresearch' project into a new self-contained minimal repo if people would like to play over the weekend

building an autonomous company

Agent Safehouse

Introduction to LLM Post-Training Techniques | PDF

Distillation Training : 4 Bits

I've been thinking a bit about continual learning recently, especially as it relates to long-running agents (and running a few toy experiments with MLX)

The Best OpenClaw Alternatives 2026 – from N… – Till Freitag

Qwen3.5 Fine-tuning Guide | Unsloth Documentation

microgpt

GLM-5

Step 3.5 Flash: Fast Enough to Think. Reliable Enough to Act.

GitHub - Search code, repositories, users, issues, pull requests...: Altered state slash commands for Claude Code. 12 substance-themed personality modes that change how

Keycloak

GitHub - zai-org/GLM-OCR: GLM-OCR: Accurate × Fast × Comprehensive

GitHub - EricLBuehler/mistral.rs: Fast, flexible LLM inference

GitHub - antirez/voxtral.c: Pure C inference of Mistral Voxtral Realtime 4B speech to text model

GitHub - alexziskind1/llama-throughput-lab: Interactive launcher and benchmarking harness for llama.cpp server throughput, with tests, sweeps, and round-robin load tools.

GitHub - qwibitai/nanoclaw: A lightweight alternative to Clawdbot / OpenClaw that runs in Apple containers for security. Connect

GitHub - moltbot/moltbot: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

GitHub - aiming-lab/SimpleMem: SimpleMem: Efficient Lifelong Memory for LLM Agents

GitHub - mikekelly/claude-sneakpeek: Get a parallel build of Claude code that unlocks feature-flagged capabilities like swarm mode.

GitHub - virattt/ai-hedge-fund: An AI Hedge Fund Team

moonshotai/Kimi-K2.5 · Hugging Face

Welcome - Poke Documentation

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

NVIDIA PersonaPlex: Natural Conversational AI With Any Role and Voice - NVIDIA ADLR

Unrolling the Codex agent loop

GitHub - different-ai/openwork: An open-source alternative to Claude Cowork, powered by OpenCode

GitHub - google/langextract: A Python library for extracting structured information from unstructured text using LLMs with precis

GitHub - memodb-io/Acontext: Data platform for context engineering. Context data platform that stores, observes and learns. Join

GitHub - rberg27/doom-coding: A guide for how to use your smartphone to code anywhere at anytime.

GitHub - bolt-foundry/gambit: Agent harness framework for building, running, and verifying LLM workflows

GitHub - unclecode/crawl4ai: 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

GitHub - finbarr/yolobox: Let your AI go full send. Your home directory stays home.

GitHub - mistralai/mistral-vibe: Minimal CLI coding agent by Mistral

GitHub - eigent-ai/eigent: Eigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity.

GitHub - NVlabs/ToolOrchestra: ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

Ask HN: What is the best way to provide continuous context to models?

Recursive Language Models

Recursive Language Models | Alex L. Zhang

Recursive Language Models: the paradigm of 2026

The Art of Context Windows: Our AI Had Alzheimer's: Here's How We Taught It To Remember

Reimagining LLM Memory: Using Context as Training Data Unlocks Models That Learn at Test-Time

Il Disclaimer muore.

GitHub - fullstackwebdev/rlm_repl: Recursive Language Models (RLMs) implementation based on the paper by Zhang, Kraska, and Khattab

Cowork: Claude Code for the rest of your work

Show HN: Agent-of-empires: OpenCode and Claude Code session manager

ToolOrchestra

OpenCode | The open source AI coding agent

You Should Write An Agent · The Fly Blog

Getting Started - SWE-agent documentation

How to Build an Agent - Amp

How to code Claude Code in 200 lines of code

SAM Audio

We Got Claude to Fine-Tune an Open Source LLM

Use Claude Code with Chrome (beta) - Claude Code Docs