AI agents
79 published articles
Agent orchestration
L'agent IA qui s'installe en 5 lignes de code et tourne 24h/24
Le framework PraisonAI permet de déployer des agents IA autonomes en 5 lignes de code, avec support de 24 LLM, protocole MCP, mémoire intégrée et détection de boucles infinies. L'instanciation prend 14 microsecondes.
2026-07-18
AI Agents
Kimi just removed the one thing keeping you from running a 24/7 AI agent
Kimi Claw deploys openClaw to the cloud with one click, eliminating local setup and hardware constraints. It runs 24/7, offers 40GB storage, and provides instant access to 5,000+ ClawHub skills through a browser.
2026-07-18
AI Research
The AI agent bottleneck isn't exploration. It's knowing what good looks like.
Two new Hugging Face papers tackle the same core problem from opposite directions: how to make AI agents reliably evaluate their own actions. AJ-Bench builds a benchmark for environment-aware judge agents, while HeavySkill argues the best judge lives inside the model's parameters.
2026-07-17
AI Agents
One agent, one memory, every app, the AI assistant that refuses to stay in its box
#1 Connect launches a cross-platform AI agent with unified memory that spans Telegram, Discord, Slack, WhatsApp, Signal, and more, no platform-locked assistant can carry context the same way.
2026-07-16
Multi-Agent Collaboration
The group chat just became AI's most dangerous proving ground
Alibaba Cloud's AgentTeams and Anthropic's Claude Tag are turning group chats into the proving ground for multi-agent collaboration. The shift from one-on-one to many-to-many conversations introduces complex challenges in context management, permission governance, and memory, and a new paradigm for how AI works inside organizations.
2026-07-16
Cloud strategy
Alibaba's AI bet: lock in the enterprise before the model race is over
Alibaba is betting the second half of 2026 on an integrated AI stack, not a single flagship model. Its strategy is to lock enterprises into its cloud via interoperable infrastructure, from agentic O&M to data warehousing, rather than to win benchmark titles.
2026-07-14
File over config
Vercel's Eve 0.22 wants your AI agents to live as files on disk, not secrets in a config
Vercel's Eve 0.22.6 brings a filesystem-based structure to AI agent development: instructions, tools, skills, and integrations all live as inspectable files, with multi-model support, human-in-the-loop prompts, and subagent orchestration.
2026-07-14
Orchestrator swap
Perplexity swapped its orchestrator model and the cost-performance chart is brutal
Perplexity swapped Grok 4.5 into Computer as its orchestrator model, claiming top accuracy on its internal benchmark at roughly half the cost of Claude Opus 4.8. The move signals a broader shift: which model you pair with an agent matters as much as the model itself.
2026-07-14
Artificial Intelligence
Meta didn't buy Manus for its chatbot. It bought the pipe that delivers 147 trillion tokens.
Meta acquires Manus for its agent infrastructure, not its chatbot. With 80 million virtual computers created and 147 trillion tokens processed, Manus becomes Meta's execution layer for enterprise automation.
2026-07-13
OpenAI vs Anthropic
OpenAI just made workers you can schedule. Claude is still a chat.
OpenAI just made workers you can schedule: persistent, shared AI agents that run in the cloud and integrate with Slack. Anthropic's Claude, focused on single-session reasoning, has no answer yet.
2026-07-13
AI IDE
Point at a button, say "fix this": Cursor's design mode finally speaks visual
Cursor's updated Design Mode lets you point, draw, or speak to an agent instead of typing instructions. The result is a faster, more intuitive way to iterate on design changes directly inside the browser.
2026-07-13
Synthetic Data Strategy
Nvidia's data atlas shows why synthetic data matters more than model weights
Nvidia's Nemotron Post-Training v3 Prompt Atlas provides an interactive map of billions of synthetic data samples, highlighting how open synthetic data is the missing layer for building reliable AI agents. The company argues that agent behavior must be inspectable and that synthetic data, released openly, is the only way to preserve proprietary signals without exposing trade secrets.
2026-07-12