Tech News
modelcontextprotocol/python-sdk v2.0.0a3
Third v2 alpha. Pre-releases are opt-in only; pip install mcp still resolves to the stable 1.x line. bash pip install mcp==2.0.0a3 or uv add "mcp==2.0.0a3" See the migration guide The 2026-07-28 spec revision drops.
Quoting Jon Udell
Human Agent in the loop I dislike the phrase “human in the loop” because it cedes authority to the machines. Let’s flip the narrative. It’s our loop, we work the same way we always have, now we recruit agents to join.
HP Inc. launches Frontier strategic partnership with OpenAI
HP Inc. scales its OpenAI Frontier partnership to deploy AI across customer experiences, software development, and enterprise operations.
Deploy a Production-Ready NVIDIA AI-Q Blueprint on Oracle Cloud Infrastructure
AI agents have changed a lot in the last two years. The first could only answer one question at a time. Then came multi-turn chat, where the model could keep.
Production-grade AI agents for financial compliance: Lessons from Stripe
In this post, you learn how Stripe built a production-grade AI agent system for financial compliance. We cover the technical architecture of Stripe’s ReAct agent framework and the infrastructure decisions behind a ded.
GitHub Repos
MemTensor/MemOS
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
# TypeScript# agent# agentic aiOpenHands/OpenHands
🙌 OpenHands: AI-Driven Development
# Python# agent# artificial intelligencejrswab/axe
A lightweight cli for running single-purpose AI agents.
# Go# ai agents# automationResearch Papers
OpenCUA: Open Foundations for Computer-Use Agents
This work proposes OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models and releases the annotation tool, datasets, code, and models to build open foundations for further CUA research.
Diversity-Aware Policy Optimization for Large Language Model Reasoning
A systematic investigation into the impact of diversity in RL-based training for LLM reasoning, and a novel diversity-aware policy optimization method that achieves a 3.5 percent average improvement across four mathematical reasoning benchmarks, while generating more diverse...
KLASS: KL-Guided Fast Inference in Masked Diffusion Models
KL-Adaptive Stability Sampling (KLASS), a fast yet effective sampling method that exploits token-level KL divergence to identify stable, high-confidence predictions that speeds up generation significantly while maintaining sample quality is introduced.