Shelbi is an open-source desktop and terminal orchestrator for coding agents such as Claude and Codex. It aims to replace the friction of juggling agents across terminal tabs with a single workspace for seeing what each one is doing, which needs attention, and which has stalled. The product is presented as a personal agent-management tool that runs as one binary and supports multiple machines. Its interface groups workspaces and agent sessions, shows their status, and offers an orchestrator, issue tracking, and changelog views. Users can work through a conversational agent interface while keeping the broader state of their projects visible.
The examples show how Shelbi is meant to preserve context and coordinate work across sessions. An agent helps specify an analytics dashboard, capturing requirements for signup, active-user, and revenue tiles; a shared metrics endpoint; date-filtered trend and plan charts; CSV export; loading and empty states; and tests. It writes these decisions to a project document and offers to turn them into tasks. In another exchange, the orchestrator reports that two API cleanup tasks - rate limiting and search pagination - cleared review overnight and merged to the main branch. The pitch is that Shelbi can help users move from discussion to documented plans and completed work without manually tracking every agent. The page promotes the tool as a way to manage agent work from one place, rather than as an account of comparative tests or measured performance against Conductor.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Richard Sutton argues that brute-force computation alone cannot produce intelligence and that AI needs clever new methods. He says the science of AI is far from finished. (twitter.com)
Anthropic is accused of charging Russian Claude users before identity checks, then cutting off access after verification and retaining biometric data. Critics say account bans can affect linked GitHub projects and Russian citizens living abroad, and accuse the company of failing to answer public questions. (twitter.com)
LLM coding agents boost workplace productivity but can prevent developers from learning through hands-on problem-solving and weaken their technical skills. Developers should preserve their expertise by building projects manually, studying fundamentals, and practicing without AI tools in their own time. (ducktape.blot.im)
A fabricated Newtype interview led The Diplomat to retract its article about a Korean startup’s AI war test in Ukraine. The retraction followed a diplomatic dispute. (thediplomat.com)
Microsoft Research’s AI Frontiers group brought together about 50 researchers to develop agent systems and foundational AI advances. After the team joined Microsoft AI in September, its research-first approach clashed with leadership’s emphasis on scaling. (hunch.net)
Microsoft researcher John Langford has left the company. Microsoft’s AI Frontiers group has been declared finished. (businessexaminer.ca)
Today's best Hacker News stories, summarized and screenshotted, one email a day.