-
AgentOS Lets You Run a Fleet of AI Agents Like a Company
Running one AI agent is easy; running many across real projects gets messy fast — which agent did what, on which task, with whose approval. AgentOS, an open-source project from SapienX, is a control surface for exactly that. It’s built on OpenClaw, which handles the agent runtime, and adds the human operating layer on top.… Continue reading
-
Uiverse Design Hands AI Agents a DESIGN.md So Sites Stop Looking Generic
You can spot an AI-built website instantly: purple gradients, pill buttons, badges, emojis everywhere. Uiverse Design, from the team behind the open-source Uiverse.io UI library, is built to kill that look. It’s a library of AI-first design systems you drop into any project — and crucially, ones an AI agent actually knows how to follow.… Continue reading
-
Krisp Voice Translation API Brings Real-Time Speech-to-Speech to Developers
Krisp, best known for AI noise cancellation, has opened its enterprise voice translation engine to developers. The new Krisp Voice Translation API — launched alongside Voice Translation v3 — does real-time, bidirectional speech-to-speech translation across 60+ languages, the same engine that hit 96% accuracy in a live healthcare deployment. ## What the Krisp Voice Translation… Continue reading
-
OrchestraML Takes an ML Project From English Prompt to Deployed Model
Building a machine learning model is still a long chain of specialized steps — finding data, cleaning it, engineering features, training, and shipping. OrchestraML compresses that whole lifecycle into a single described goal. You tell it what you want in plain English, and its agents handle the rest, with a human signing off at every… Continue reading
-
Kimi Work Turns Moonshot K2.6 Into a Full AI Workspace
Most AI tools are a box you paste a prompt into. Kimi Work, Moonshot AI’s new desktop for knowledge work, is built on a different premise: real work spans documents, research, and code, so the AI should live across all of it rather than in a single chat window. It’s powered by Moonshot’s Kimi K2.6… Continue reading
-
Astra Autonomous Pentest Sends AI-Found Fixes Straight Into Your IDE
Penetration testing has always been slow, manual, and expensive. Astra’s new Autonomous Pentest turns it into a pipeline of AI agents, built on insights from more than 5,000 real-world pentests, that own the full cycle — from finding a bug to handing a developer the fix. ## How Astra Autonomous Pentest works Discovery agents hunt… Continue reading
-
MetaMask Agent Wallet Lets AI Agents Trade DeFi With Guardrails
Letting an AI agent touch your crypto has been a scary proposition — one bad transaction and the funds are gone. MetaMask Agent Wallet, which opened early access on June 8, is built to make that safer. It’s a self-custodial wallet designed for AI agents, giving them access to swaps, perpetual futures, prediction markets, and… Continue reading
-
ChatGPT Dreaming Gives It Memory That Updates Itself Over Time
OpenAI is rolling out a rebuilt memory system for ChatGPT, called Dreaming, that changes how the assistant remembers you. Instead of just storing facts as you mention them, Dreaming runs a background process that synthesizes memory over time and keeps it current. ## How ChatGPT Dreaming works The standout behavior is that memories age. If… Continue reading
-
Claude Opus 4.8 Runs Up to 1,000 Subagents in a Single Session
Anthropic released Claude Opus 4.8 on May 28, just 41 days after 4.7, and the headline isn’t a benchmark bump — it’s a new way of working called dynamic workflows. In Claude Code, the model can now plan a large task, write a JavaScript orchestration script, and spin up as many as 1,000 subagents running… Continue reading
-
dots.tts Is a New Open-Source TTS Model With No Discrete Tokens
Most text-to-speech systems convert audio into discrete tokens at some stage of the pipeline. dots.tts, a new open-source TTS model from RedNote’s Hilab team, throws that step out entirely. It’s a 2B-parameter, fully continuous, end-to-end autoregressive system — a semantic encoder, an LLM, and a flow-matching acoustic head running over a 48kHz AudioVAE, with no… Continue reading
