Kilo CLI 1.0 Launches with Support for Over 500 AI Models
Kilo, an AI coding startup, launched Kilo CLI 1.0 this week, a command-line tool supporting over 500 AI models from both proprietary and open-source providers, including Alibaba's Qwen. The release, a complete rebuild of the original CLI, aims to provide developers with flexibility in their choice of development environments, according to VentureBeat.
The launch of Kilo CLI 1.0 follows the recent release of Kilo's Slackbot, which allows developers to ship code directly from Slack, powered by MiniMax, a Chinese AI startup. According to VentureBeat, Kilo is backed by GitLab co-founder Sid Sijbrandij.
In other tech news, the demand for AI is driving unprecedented investment in massive data centers, leading to a search for energy sources to support their computational needs, according to MIT Technology Review. Next-generation nuclear power plants are being considered as a potential solution, offering potentially cheaper construction and safer operation compared to older plants. MIT Technology Review recently held a subscriber-exclusive roundtable discussion on hyperscale AI data centers and next-gen nuclear technologies.
Meanwhile, in Michigan's Upper Peninsula, the Eagle Mine, the only active nickel mine in the US, is testing a new process to extract more nickel from lower-quality ore, according to MIT Technology Review. The mine's owner is using a fermentation-derived broth developed by Allonnia to capture and remove impurities. Kent Sorenson, Allonnia's chief technology officer, stated that this approach could help companies continue operating sites with declining ore quality.
In the realm of Linux kernel development, Kairui Song outlined a plan to simplify and optimize the kernel's swap code at the 2025 Linux Storage, Filesystem, Memory-Management and BPF Summit, according to Hacker News. The kernel's swap subsystem is a critical component in memory management and significantly impacts system performance.
Finally, Protegrity highlighted the importance of securing agentic systems in a recent article published by MIT Technology Review. The article emphasizes treating agents like powerful, semi-autonomous users and enforcing rules at the boundaries where they interact with identity, tools, data, and outputs. The article presented an eight-step plan for CEOs to implement and report against, focusing on governing agentic systems at the boundary.
Discussion
AI Experts & Community
Be the first to comment