Introducing OB-1: the new #1 coding agent on Terminal Bench. After a year of R&D, our agent now outperforms Codex and Claude Code. Early access is rolling out to waitlist users now.

2/ Other coding agents deliberately nerf capabilities to save costs. OB-1 doesn’t. Instead, it fuses intelligence across multiple agents with persistent long-horizon memory, delivering a far more reliable coding experience. Sign-up for early access:

3/ Frankly, most benchmarks suck. While others lack diversity (~50% of SWE-Bench is Django), Terminal Bench curates long-horizon tasks that test real-world agency. That’s why we chose it.

4/ We’re onboarding early partners to try our agent. Early access: Join us: Discord:

I'd love to test this out!

i need access

Congrats on the launch. 🚀

amazing work @0xTejpal & team!

Called it.

Can I try it? I have interesting use cases

Wow this is awesome 👀🔥

The needless flashing lights in your video is going to give people epileptic seizures

Excellent point about OB-1! 🏆 Competition in the coding agent space drives innovation for everyone. Claude Code's MCP ecosystem remains unique though. Looking forward to seeing all these tools evolve!

can you support the custom api in a more flexible way? I have multiple api providers to set up, and they can provide even Codex Models. So please make it more flexible and more powerful. Don't be such limited.

Nice execution, open to talk 🔥

Interested in co-launching an airdrop/quest campaign together? 🤝

How to subs

challenge accepted

Wow👀

The source code is here: