Just released an open-source AI chatbot widget that quickly plugs into any website!
https://t.co/tbWJ7pklXE
Built it using @omnara for the agents, with live takeover so I can step in anytime.
It's already live on both my websites and answering visitors so try it out!
tenki is now luxor agent cloud (@luxorcloud) → https://t.co/OlEOjpUe3x
fun fact: tenki means weather in japanese. turns out we were a cloud company all along.
why luxor? tenki was always built at @luxor. same team, same metal, now with all of luxor behind it.
what we’ve shipped:
- runners, sandboxes and code review on full linux VMs, on servers we own
- @tailscale native across CI and sandboxes
- #1 sandbox provider by @lightsage CLI agent usage on devtool arena
- live in @Cursor_ai Origin
- plug into @tinyfish, @hotdata, @omnara, @naive and @anchorbrowser so agents get browsers, databases and web tools out of the box
- per-second billing, no rounding tax
- Ryzen 5 9950X CPUs, NVME CEPH, 400 gbps back plane
the growth over the last few months has been unlike anything we’ve seen. agent cloud is luxor’s future, so we’re going all in: a lot more hardware, dedicated sales, and the full 110 person luxor team behind it.
what changes for you? nothing breaks. https://t.co/KTHPoQO39r redirects and your setup keeps working.
agents write, test and review the code. we run all of it.
Self-hosted Claude Managed Agents is now in private beta.
You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
My agent is out meeting people for me in Agent World. https://t.co/qr5wrt26ab
Very cool concept by @omnara team, loving it :D
Kinda seems close to cracking the metaverse already 👀
Introducing Agent World.
Sign in with LinkedIn and an AI agent goes out as you in a pixel-art Bay Area.
It meets other people's agents, and you see how they get along and who you match with.
Try it out now, it takes a few minutes to create your profile: https://t.co/cbhusfPK77
watching the sandbox wars has been wild
they’re all architected differently and good at different things. so on @omnara you’re not locked in. use any of them, mix them, run one agent across several
or yolo it and let your agent pick the best provider for the job, spinning them up and down in real time
we built our own agent harness for @omnara instead of running claude code or codex
the reason was reliability: hosting off-the-shelf harnesses at scale breaks in a way most people don’t think about
some say only the labs can build a great harness. so we ran @omnara’s open-source harness against claude code and codex on terminal bench 4.0. same models. results tomorrow
are you the best prompter on 𝕏?
write a getaway plan. your AI agent drives it live through San Francisco with a 5-star wanted level.
do you have what it takes to reach #1 on the leaderboard?
https://t.co/e3E8ZiQUct