JUST SHIPPED: Open-source cross language multi-agent contract compliance team using Google ADK and A2A. Python agent and Go agent work together as a team. 100% Opensource code with step-by-step tutorial.
SYSTEMS
-
Intelligence at the periphery, proof at the center, authority at the human frontier
By
–
ALPHA AGI NODE v0 Intelligence at the periphery. Proof at the center. Authority at the human frontier. http://montrealai.github.io/goalos-agialpha-ascension/agi-alpha-node-v0.html #AGIALPHA #MontrealAI
-
LangSmith Engine identifies issues, clusters patterns, and fixes agents
By
–
That's why we built LangSmith Engine, an agent built to improve your agent. Engine identifies issues from traces, clusters patterns, drafts fixes, and proposes evals to prevent regressions. Connect your tracing project + start improving your agent today:
-
Teams lack a continuous improvement system for their agents
By
–
Most teams building today have traces, what they don't have is a system for continuously improving their agents.
— LangChain (@LangChain) 23 juin 2026
The teams that do use an agent development lifecycle: build, test, deploy, and monitor.
The problem with this lifecycle? It scales at the speed of their engineers. pic.twitter.com/YlXt3BRrQ2Most teams that build today have traces, what they don't have is a system to continuously improve their agents. Teams that use an agent development lifecycle: build, test, deploy, and monitor. The problem
-
Bringing long-horizon agentic workflows to everyone
By
–
bringing long-horizon agentic workflows to the masses
-
Ling and Ring Technical Report 2.6 on Large-Scale Agentic Intelligence
By
–
Ling and Ring Technical Report 2.6 Efficient and Instantaneous Agentic Intelligence at the Scale of Trillions of Parameters
-
Loop Engineering Cycle: Build Systems That Improve Every Run
By
–
Loop engineering cycle for AI Product Managers. For the last two years PMs have been trying to write the perfect prompts. The better move is to stop prompting one-off and start building loops. A loop is a system that improves every time it runs. At the center is a reusable
-
Initial deployment: small step, essential repeatable improvement cycle
By
–
One thing we have observed quite consistently: deploying the first version is only a small part of the work. A key part of building reliable agents is having a repeatable lifecycle to improve them over time.
-
AI in 2040: Nearly Optimal Stack, Massive Current Inefficiency
By
–
AI in 2040 will not be built on the stack we use today. It will be much closer to optimal. The current stack exhibits 3-4 orders of magnitude data inefficiency and 4-5 orders of magnitude compute inefficiency. Nearly optimal AI is what
-
NVIDIA Agent Toolkit: AI agents for workflows
By
–
Specialized AI agents help enterprises turn AI into systems built for their own workflows.
— NVIDIA (@nvidia) 23 juin 2026
NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work.
Learn more:… pic.twitter.com/rPsXufoTHDSpecialized AI agents help businesses transform AI into systems designed for their own workflows. The NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills, and secure runtime support to help teams