ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK.
It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass.
How to run it:
1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart.
2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done.
3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents.
Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens.
Bookmark this.
Head of Claude Code:
"Fable 5 is our most powerful model for running self-improving agent systems.
Add /loops, dynamic workflows, dreaming - and you are unstoppable."
In 12 minutes, the Head of Claude shows you how to build self-improving agent systems with Fable 5 from scratch.
Worth more than a $500 agent-building course.
Watch today. Then learn how to run the same setup in just a few clicks with Adaline ↓
Anthropic disabled Fable 5 for everyone over what they call a 'narrow jailbreak,' and say they're working to restore it. Here's what the model that just went dark actually does:
This is my loop
I built a SaaS that posts to Instagram + TikTok 24/7
I don't write the captions. I don't pick the music. I don't touch it
The stack that runs it while I sleep:
> PHP 8.3, no framework
> Caddy web server
> SQLite in WAL mode
> Cloudflare R2 for video storage
> Cloudflare Tunnel, no open ports
> Stripe for billing
> OpenAI writes every caption
> ffmpeg muxes the music
> Zernio publishes to IG + TikTok
> Vanilla JS + CSS on the front
> one cron job that loops forever
No Next.js. No Kubernetes. No VC
Andrej Karpathy:
“Vibe coding is incredible. But agentic engineering is the next level.
90% of my coding routine is automated by AI agents.”
In this 30-minute talk, Andrej Karpathy explains how to build an AI agent workflow from scratch.
Worth more than 500$ agentic engineering course on the internet.
Watch it today, then read the article below.
All types of databases, Redis, Postgres, Clickhouse, Mysql etc. now display important stats and metrics aswell as most run queries in the Maple service map
New episode with @AviFelman sitting down with @Rewkang on the next mega bubble.
The total market cap of all private robotics companies is $200B.
XRP is $100B.
Pokémon trading cards are $50B.
This is going to be a $10 TRILLION industry.
We discuss:
• VCs are pivoting from software → physical AI
• The GPT-3 moment for robotics
• Why you can't just hook Claude up to a robot
• How @Rewkang built @RoboStrategy ($BOT)
• Portfolio: Figure, Apptronik, Standard Bots, Dyna, Dexmate
OUT NOW on @YouTube & @Spotify 👇
Anthropic's in trouble, again!
They spent years building what's now fully open-source.
What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box.
For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response.
Every major AI product tried to replicate it.
But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK.
So teams started building an owned version that required engineering the entire interface layer from scratch.
Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it.
To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run.
@CopilotKit is now the only open-source framework that actually lets you build your own full-stack Claude-like apps.
It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication).
Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice.
In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like:
- generative UI, so the agent renders real components instead of text
- chat windows, sidebars, and popups, or a fully headless setup
- shared state, so the agent and app stay in sync
- human-in-the-loop approvals, where the agent waits before acting
- persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text
And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time.
The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team.
CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more.
CopilotKit GitHub repo → https://t.co/wkQ1taF0rM
(don't forget to star it ⭐ )
If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation.
Read it below.
My article "How To Investigate A Person Of Interest In 2026" is now available as a PDF.
A practical guide to digital footprint analysis – from email reconstruction to metadata mining and entity graphing.
Thanks @osintnewsletter for the mention.
PDF: https://t.co/86YlE9e2pB
Anthropic engineer:
"You're not supposed to watch Claude Code work. You're supposed to wake up and review what it shipped."
In 22 minutes she builds the entire workflow live on camera.
Most people close their terminal and everything stops.
This setup keeps shipping while you sleep.
Watch the video, then save the exact setup below👇
Anthropic quietly dropped an official plugin that scans your project & sets up hooks, skills, MCP servers, subagents & automations.
Most people are running Claude Code at 20% of what it can do.
/plugin install claude-code-setup@claude-plugins-official
autoreview is the most impactful skill I've added to my stack (next to https://t.co/SEj2XRpaD1). It automatically reviews your code before landing a PR.
Finds so many edge cases.
Sometimes it runs for hours.
https://t.co/zbUjIS2e1i
I did it 👍 thanks @levelsio for sharing.
Setup @Tailscale on my @Hetzner_Online VPS 🙌
Installed @claudeai on VPS 🤞
All my sites run through @Cloudflare tunnels 😎
Got @TermiusHQ running locally on my Mac and iPhone ❤️
Locked all the ports 💪
Migrate 25GB of projects, websites, apps onto my VPS. All MD files there as well 🏋️♀️
Then went shopping with the wife while coding from my phone and I’m no coder.
This means I can check daily tasks, fix minor bugs and constantly and work on our main Shopify site.
I’m launching a daily deals section all automated with resend but I can build and tweak that without needing to be at my MacBook.
And if someone says you should be present when shopping. Fuck that. I’m present when 99% around my family and kids.
the fastest growing GitHub repos in finance this week:
1. TauricResearch / TradingAgents (+3,500 ⭐)
A multi-agent LLM framework for financial trading: multiple AI agents (analyst, risk manager, trader) collaboratively make investment decisions based on news and market data.
2. brokermr810 / QuantDinger (+989 ⭐)
An AI-powered quantitative trading platform for crypto, stocks, and forex: backtesting, live trading, multi-agent market research, with support for Binance, Alpaca, and MT5.
3. himself65 / finance-skills (+510 ⭐)
A collection of AI skills for financial analysis and trading: ready-to-use tools for agents (Claude Code, MCP) as technical analysis, stock valuation, financial report parsing.
4. OpenBB-finance / OpenBB (+200 ⭐)
An open-source financial analysis platform with AI agent support: data on stocks, crypto, derivatives, and macro indicators; Python SDK + terminal; a Bloomberg alternative for developers.
5. ericosiu / ai-marketing-skills (+107 ⭐)
Open-source AI skills for marketing and finance automation: growth experiments, sales pipeline, SEO, outbound, and financial ops. All powered by AI agents.
6. AI4Finance-Foundation / FinGPT (20,300 ⭐)
Open-source financial large language models: fine-tuned LLMs on financial data, sentiment analysis, robo-advisor, technical analysis; models published on HuggingFace.
7. microsoft / qlib (43,400 ⭐)
Microsoft's AI-oriented quantitative investment platform: end-to-end pipeline from idea to strategy execution; machine learning for quant research, backtesting, and live trading.
8. AI4Finance-Foundation / FinRL (15,200 ⭐)
A reinforcement learning framework for finance: automated trading strategies, portfolio management, training agents on real market data.
9. KylinMountain / TradingAgents-AShare (+80 ⭐)
A multi-agent investment research system for the Chinese A-Share stock market: 15 AI agents simulating an investment bank workflow — debates, visualization, integration with Claude Code.
10. Lumiwealth / lumibot (1,592 ⭐)
Backtestable AI trading agents: support for stocks, options, crypto, futures, and forex; integrations with Interactive Brokers and Alpaca; LLM agents for SEC filing analysis and macro data.
bookmark this and start today.
Dear frontend devs and UI designers. I bring you Liquid DOM, a complete and faithful implementation of Liquid Glass on the Web.
- Shape morphing
- All properties animatable
- Dynamic refraction and reflection
- Adaptive tint
- Adaptive specular highlight
- Dispersion
- Full html integration
- Super fast layout engine that works across Canvas and html
- Pointer event handling
- Framework and renderer-agnostic low level API
- High level React API
- Ootb @threejs and r3f integration
And lots more.
Read on for implementation details and demos.