Cle
57 posts




Been working on something similar to t3code for a few days now. Codex 5.3, GPT 5.4 for backend are so good and reliable, and while Opus and Sonnet are great at designing landing pages, component-level UI design and general UI/UX still feels so off and moderate.

OpenCode is about to get more powerful with remote sandboxes I showed a brief demo before, but here's a much more in-depth demo. it's not hard to add basic support for a remote env, but handling all the edge cases like when a remote env gets deleted is difficult. especially if care about good UX You never want to lose session data. so the choices are: run the session in your env, but run all tool calls remotely. that's too complex and painful. The other way is to just let the full session run remotely, but sync back all the session data in your env. We chose this path: we built a syncing system which logs all events in a way that we can always recreate your entire session. That means the remote env could get destroyed, but we can easily restore it. it also opens up other interesting ideas which we'll be exploring

New in Claude Code: Remote Control. Kick off a task in your terminal and pick it up from your phone while you take a walk or join a meeting. Claude keeps running on your machine, and you can control the session from the Claude app or claude.ai/code

@cle_112 Yes, coming soon! The team is not just building the app for Windows, but also making sure the agent works well in a Windows sandbox. You can get notified when it’s ready here: openai.com/form/codex-app/






The agentic economy is accelerating and it’s far more exciting than anyone had imagined. Moltbook made it to the mainstream: agents interacting, competing, settling, coordinating. Even @elonmusk engaged with the idea of agent courts (Moltcourt on EigenCloud). Single-player agents can run anywhere and don’t need verifiability. But multi-player agents (serving many users or other agents) need trust: verifiability and privacy. Prove the agent ran this code, used this data, can upgrade only via this process, and keeps data inside its container. That is real agent identity: code + data + upgrades + state. Next up are sovereign agents: ownerless agents like Bitcoin. Musicians, journalists, teachers earning, spending, compounding on their own. We built EigenCloud for verifiable and sovereign agents so open innovation can scale to high stakes real world use cases. Open Innovation Challenge: Build a verifiable or sovereign agent by Feb 20. Top 5 get EigenCompute credits, I’m putting up $10,000 for the best! No tokenized agents.


we're hiring vibe coders! if you love shipping fast, mobile apps, and creating content reply and I'll send more details













