Moonshot published the Kimi K3 weights. The model is 2.8 trillion parameters with a 1 million token context window, shipped in MXFP4 at roughly 594GB. Within a day it was […]
Category: AI
Superagentic AI Speaks on RLM at the AI Engineer World’s Fair 2026
Superagentic AI returned to the AI Engineer World’s Fair 2026 Online Track with a second talk, “RLM: Recursive Language Models for Large Codebases.” The session, delivered by Shashi Jagtap, Founder […]
Superagentic AI at the Google I/O and CAIS Conference: Reflections from Bay Area
Last week, I returned to London from the San Francisco Bay Area with renewed energy, fresh insights, and a deep appreciation for the people driving artificial intelligence forward. Since back, […]
PyFlue 0.2.0: Bringing Flue’s Agent Runtime Model to Python
PyFlue 0.2.0 is now available. This release is a major step toward parity with the TypeScript Flue framework and introduces a clearer runtime model for building production-oriented Python agents. The […]
Agentic Harness Engineering: The Next Frontier After Harness Engineering
Harness Engineering has become AI trend these days and now it reached to the next level. In our earlier post, Harness Engineering: The Hottest Topic in AI Agent Engineering, we […]
Launching the London Agentic AI Community Website
Superagentic AI is excited to announce the launch of the new official website for London Agentic AI, a community created for engineers, researchers, founders, and practitioners building real-world AI agents […]
New OpenAI Agents SDK: The Dawn of Extreme Harness Engineering
OpenAI released a major evolution of its Agents SDK as a fundamental rethinking of how agents should operate in production. They introduced an open, inspectable harness for orchestration and a clean […]
Official Meta-Harness Repo + Packaged Power = Coding Agent metaharness
Stanford IRIS Lab officially released the reference code for Meta-Harness, their groundbreaking framework for autonomously optimizing the code scaffolding around a fixed large language model. The announcement quickly gained traction […]
Open Memory and Open Harness Is Not Enough: You Need Self-Optimizing (Self-Healing) Harness
Recently there is a lot of discussion on agent Main and harness initially anthropic put a blog post on scaling managed agents which gone viral is and replied to that […]
What OpenClaw Vs Anthropic Drama Taught Us: The Urgent Need for Self-Optimizing Harness Engineering
Recently, OpenClaw took off like a one of the greatest breakthrough in the AI. People are going crazy to setup OpenClaw to automate the tasks. All looked very good until […]