Après six mois de désaccords, le Sénat et l’Assemblée nationale ont définitivement adopté une version commune du texte le 21 juillet, dernier jour possible pour tenter de tenir le délai fixé par Emmanuel Macron, qui veut voir la mesure appliquée dès le 1er septembre.

Le deuxième texte le plus soutenu depuis la création de la plateforme des pétitions citoyennes de l’Assemblée, avec 732 000 signataires, dénonçait une « atteinte grave à l’État de droit ». Les député…

Added Registry skills content store and manifest for skill discovery Config schema exposed through ACP Checkpointer engine state model, owner union, and pending hunks Changed [Breaking — hooks] ...

Rejoignez la coopérative...

What is the difference between Chat Control 1.0 and Chat Control 2.0? A clear overview of both EU laws, their timelines, and where things stand today.

Today, the European Parliament allowed the suspicionless mass scanning of private communications ("Chat Control 1.0") to pass, a measure it had rejected twice in March. Although a majority of voting M...

Not the US Hosting and Still Not Paying Moms.

Like RSS and Google Reader.

By Ryan Lopopolo, Member of the Technical Staff

A middle finger to Spotify!

New from Fly.io today: Sprites.dev. Here’s their blog post and YouTube demo. It’s an interesting new product that’s quite difficult to explain—Fly call it “Stateful sandbox environments with checkpoint & …

Formats over apps.

We help you find European alternatives for digital service and products, like cloud services and SaaS products.

Exploring five critical questions shaping software engineering through 2026, with contrasting scenarios for each. These lenses help prepare for the evolving ...

What 2025’s AI research told us about developer productivity and identity, and why enablement matters more than tool choice.

2025 Year in Review of LLM paradigm changes

Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills …

Claude Sonnet 4.5 is the best coding model in the world, strongest model for building complex agents, and best model at using computers.

Every day I seem to run into yet another post with someone solemnly opining that “writing code has never been the hardest part of software engineering. And hey, that’s smashing.

Universal AI agent configuration parser and converter - johnlindquist/dotagent