yeah this 2023 babyagi diagram was on point 🙂 thx! seems like if you keep going meta, you'll end up with something like activegraph, lots of ppl seem to have been circling similar ideas
AGENTS
-
NVIDIA’s Jensen Huang details enterprise agent stack and toolkit
By
–
Agents need more than a model.
— NVIDIA (@nvidia) 3 juin 2026
Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together.
This is the NVIDIA toolkit for agents: https://t.co/j6KJhOwZ5B pic.twitter.com/XdWSaTS59KAgents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents: https://
nvda.ws/4em0o8l -
OpenShell v0.0.55 adds Vertex AI support and policy visibility
By
–
OpenShell v0.0.55 Google Vertex AI inference provider Profile-backed policy visibility Better Podman detection in the gateway Restored GPU procfs baseline behavior CI and docs fixes Run agents against Vertex AI, with improved policy visibility and more
-
Zeely: Emotionally adaptive AI experience launching in 2 days
By
–
Emotionless AI is getting left behind.
— God of Prompt (@godofprompt) 3 juin 2026
The next wave won’t just answer prompts, it’ll read tone, adapt emotionally, and make every interaction feel alive.
Zeely is turning AI from “tool” into “experience.”
Drops in 2 days. Don’t blink. https://t.co/rROFrY1ebLEmotionless AI is getting left behind. The next wave won’t just answer prompts, it’ll read tone, adapt emotionally, and make every interaction feel alive. Zeely is turning AI from “tool” into “experience.” Drops in 2 days. Don’t blink.
-
SambaNova post about Intel’s rack-scale agentic AI design
By
–
Agentic AI needs CPUs, GPUs, and AI accelerators working together. @TheRegister highlights @intel
's new rack-scale agentic AI designs and the first customer deployment of the Intel + SambaNova disaggregated inference blueprint through VC2. The result: GPUs handle prefill, -
Develop Physical AI Reasoning, World, and Action Models with NVIDIA
By
–
Develop Physical AI Reasoning, World, and Action Models with NVIDIA! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux
-
Microsoft’s SkillOpt: Text-Space Optimization for Frozen Agent
By
–
SkillOpt: Microsoft's Announces Text-Space Optimization for Frozen Agent! #BigData #Analytics #DataScience #AI #MachineLearning #NLProc #LLM #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux
-
Claude Code: Agent control planes, not just workflow generation
By
–
On the surface, it's Claude Code generating workflows on its own, but digging deeper, it's the control plane of agent products that's changing. In the past, we crammed complex tasks into a long context, expecting the model to remember the goal, break down steps, and judge
-
Revnu replaces a growth team with a single agent
By
–
En 2026 ya no necesitas contratar un equipo de growth.
— Nico (@nicos_ai) 3 juin 2026
Conectas Revnu a tus herramientas y por la mañana te llega un Slack con lo que movió.
SEO, ads, outbound, churn winback… todo en un agente.
Lo que antes costaba 3 personas, ahora cuesta casi nada. https://t.co/yaWcfa0CIn pic.twitter.com/vKApwolccUIn 2026, you no longer need to hire a growth team. You connect Revnu to your tools and in the morning, you receive a Slack with what has moved. SEO, ads, outbound, churn winback… all in a single agent. What used to cost 3 people now costs almost nothing.
-
Nitrosend: One Prompt Writes, Designs, and Sends to 10,000
By
–
This is the part nobody saw coming. You don't log into Nitrosend, you just tell it what you want and the email lands in 10,000 inboxes.
— AI Highlight (@AIHighlight) 3 juin 2026
One prompt did the writing, the design, and the send. The dashboard is officially extinct. https://t.co/n5dFsooyWBThis is the part nobody saw coming. You don't log into Nitrosend, you just tell it what you want and the email lands in 10,000 inboxes. One prompt did the writing, the design, and the send. The dashboard is officially extinct.