It is awesome (I use it as a shared brain for my Hermes and OpenClaw Agents)
AGENTS
-

Databricks Apps & Agents for Good Hackathon at Data + AI Summit 2026
By
–



The Databricks Apps & Agents for Good Hackathon is back at #DataAISummit 2026! In partnership with @OpenAI
, this two-day hackathon brings developers, engineers, and AI builders together to create agentic data applications for social impact using Lakebase, Agent Bricks, and -

Codex Agent Automates JAX Transformer Coding Challenge
By
–
Couple days back @swyx posted a challenge: code a ~10M transformer in JAX/Flax/Optax, run it in free Colab, and train it on addition w/ your agent! I gave Codex the screenshot + /goal. It controlled Colab through Chrome, used my signed-in session, handled runtime/editing
-

Teaching Claude Code Basics in an Accessible Way
By
–


I'm a big advocate for teaching more people the fundamentals of using Claude Code in an accessible manner. Much of the world hasn't yet used AI agents, and there's a huge opportunity to level the playing field and broaden access.
-
AI Agents for Automated Code Hardening and Audit
By
–
Kakuna: skills with checklists that only know how to harden your codebase /plan with it then let it /goal for a day, it comes back with same functionality but all the boring stuff done for you + an audit of its own work. focus on subagent parallelism and encodes strong
-

Building autonomous AI agents with reasoning, planning, and adaptation
By
–
Building Agentic AI Systems — Create intelligent, autonomous AI agents that can reason, plan, and adapt: http://
amzn.to/4dvxf8Z via @PacktDataML 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼: Understand the foundations and advanced techniques of building intelligent, autonomous AI agents -
Open Source Deep Research for Agent Harnesses with AI-Q Skills
By
–
Say hello to open source deep research for your favorite agent harness.
— NVIDIA AI (@NVIDIAAI) 22 mai 2026
Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back… pic.twitter.com/u7tVWvCUWdSay hello to open source deep research for your favorite agent harness. Our AI-Q agent skill packages the work of building a research pipeline into a portable skill. Drop it into your harness, and the agent delegates a research task to a local or hosted AI-Q server and gets back
-
Fixing vibe-coded apps with Replit Agent authentication
By
–
Most vibe-coded apps forget every user who opens them.
— Replit ⠕ (@Replit) 22 mai 2026
With one prompt to Replit Agent fixes it! 💻
Try adding authentication to your app today! pic.twitter.com/8742R0FulzMost vibe-coded apps forget every user who opens them.
With one prompt to Replit Agent fixes it! Try adding authentication to your app today! -
Autonomous AI Partner for Data Pipelines in Lakeflow
By
–
🧞 Genie Code brings an autonomous AI partner directly into Lakeflow, helping data engineers build, orchestrate, monitor, and debug pipelines and jobs from a single agent experience.
— Databricks (@databricks) 22 mai 2026
With natural language, teams can:
• Generate production-ready pipelines and orchestrate jobs
•… pic.twitter.com/9zy2S2yvOrGenie Code brings an autonomous AI partner directly into Lakeflow, helping data engineers build, orchestrate, monitor, and debug pipelines and jobs from a single agent experience. With natural language, teams can:
• Generate production-ready pipelines and orchestrate jobs
• -
Hyperagent simplifies AI agents with cloud sessions and Slack deployment
By
–
The team that made databases feel easy just did the same thing for AI agents.
— Chubby♨️ (@kimmonismus) 22 mai 2026
Hyperagent gives you a full cloud environment per session, browser, shell, code execution, integrations, no local setup. You build an agent, deploy it to Slack, and it runs your workflows while you do… https://t.co/xJdnlMYoXzThe team that made databases feel easy just did the same thing for AI agents. Hyperagent gives you a full cloud environment per session, browser, shell, code execution, integrations, no local setup. You build an agent, deploy it to Slack, and it runs your workflows while you do
