I tend to stay away from this type of stuff: 1. Insanely crowded
2. Big labs are moving in
3. Hard to make $
4. As coding models get better, boilerplate/frameworks will make things harder, not easier
5. Having built dozens of agents over the years, custom wins almost every time
AGENTS
-
Custom AI Agents Beat Generic Frameworks Every Time
By
–
-

Gemini 2.5 Deep Think Sets New Frontier Math Record
By
–
Gemini 2.5 Deep Think consigue un nuevo record en Frontier Math, evaluado por la buena gente de Epoch
-

Billions of robots smarter than humans: opportunity or threat?
By
–
Ça vous inquiète ou ça vous enthousiasme L’arrivée de milliards de robots plus intelligents que les humains
-

New Gemini Enterprise capabilities for contextual data and agents
By
–
Today we're rolling out a whole slew of new capabilities for using contextual data relevant to you and your organization and for building and using agent-based systems on top of Gemini and @googlecloud!
— Jeff Dean (@JeffDean) 9 octobre 2025
Learn more at:https://t.co/xLr0HK3PHE
Using Gemini and agents to extract… pic.twitter.com/nMikGSnGFSToday we're rolling out a whole slew of new capabilities for using contextual data relevant to you and your organization and for building and using agent-based systems on top of Gemini and @googlecloud
! Learn more at: https://
cloud.google.com/blog/products/
ai-machine-learning/introducing-gemini-enterprise
… Using Gemini and agents to extract -
Super Mario Kart AI racers lacked random items due to compute limits
By
–
And at the same time In Super Mario Kart (SNES) the AI racers couldn’t get random items because of compute limitations (implementing individual random generators would have been to costly)
-
BEHAVIOR Challenge Invites Global Robotics Submissions
By
–
The robotics research community is invited to participate in a competition that seeks to shape the future of domestic robotics! The BEHAVIOR Challenge, built upon years of meticulous development & simulation work, welcomes submissions worldwide by Nov. 15:
-
Graph-based long-term memory maintains consistent context across sessions
By
–
It tracks entities and relations through a graph structure, so updates merge context instead of replacing it. That’s what keeps long-term memory consistent over multiple sessions.
-

Mem0: Open-Source Memory Layer for AI Agents
By
–
Build AI agents with scalable long-term memory! Mem0 is a fully open-source memory layer that gives AI agents persistent, contextual memory across sessions. Without memory, agents reset after every interaction, losing context and continuity, which limits their usefulness in
