226 stories
This week at LobeHub: drive Claude Code and Codex from LobeHub, DeepSeek v4 Pro and GPT Image 2 land, the CLI gets its own landing page, and a sweep of copy refinements across the product.
This week at LobeHub: page edit history ships, our repo crosses 10,000 commits, and René shares an essay on how wording shapes product experience.
Olli-Pekka Heinisuo on how open-source code becomes useful context for coding agents, from generic answers to grounded examples from real repos.
This week at LobeHub: customizable sidebar, inline prompt refinement and translation for image and video generation, and our launch on Peerlist.
This week at LobeHub: inline suggestions in the input field, a one-click CLI to migrate from OpenClaw, IM bots that can read photos and videos, and why owning your infrastructure matters.
This week at LobeHub: IM integration launches on Product Hunt, the mobile app ships on iOS and Android (bugs and all), and agents take another step out of the browser.
This week at LobeHub: a reliability wake-up call, three model integrations in one week, what happens when providers go overloaded, native IM integration progress, and what LOL is teaching us about editorial judgment.
The hardest thing about building an open source app is staying connected to your own work. A reflection on how maker becomes maintainer, and why protecting the space to build from a personal place matters.
This week at LobeHub: UI refreshed, BM25 search makes Cmd+K instant, we design an S3-inspired permission system for agent documents, the team debates what knowledge is worth in the AI era, and a new mascot is born — Lobster.
Introducing Lobe Open Log (LOL), our weekly dev blog inspired by Factorio Friday Facts. Join us as we share what we are building, how we think, and where LobeHub is heading.
Donut Browser ships with zero telemetry: no usage tracking, no analytics endpoints, no phone-home requests. Here's why that choice is deliberate.
Author: Lucy Liu Note: this blog post is a cross-post of a Quansight Labs blog post.
Millions of isolated SQLite databases that scale to zero, run at the edge, and stream changes to your React frontend in realtime.
Per-actor durable queues with a programmable run handler. Ordered processing, request/response, traffic spike absorption, and workflow integration.
Durable, replayable workflows for TypeScript. Sleep, join, race, retry, rollback, and human-in-the-loop with realtime frontend integration.
Two shipping dates, one product line. Radar OSS in January, Radar Cloud in February. Here's the scope, the split, and what won't make it into v1.
User experience (UX) has always been an important focus for scikit-learn. As we know, UX encompasses many aspects, but here we will focus specifically on how easy it is for the user to understand scikit-learn models during development, especially while using tools like jupyter notebooks.
Radar is an open-source Kubernetes UI with a built-in MCP server for AI agents. Run it locally against any kubeconfig or deploy it in-cluster with Helm.
Showing 216 of 226 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
