James Xian

[James Xian @xranthoar]

@jiayq This has been long awaited! Glad to be on the journey again!

[Yangqing Jia @jiayq]

We are starting Intent Lab, building an autonomous team we call "fleet" that turns intent into production software. Today we are sharing some early results: the fastest GLM5.2 inference engine, one shot database creation, and a fully verified agent filesystem.

https://t.co/CtwtypE0rH

[James Xian @xranthoar]

Huge congrats to @Guanlan 🎉 A founder who truly gets first principles — building infra that’s useful and reliable. Proud to have backed this early and to be building alongside you.

[Guanlan Dai @guanlan]

Today we're announcing @runta's $20M seed, led by @a16z.
Software is constrained when you write it. Agents have to be constrained while they run.
Runta is the execution layer that controls what AI agents can actually do.

[James Xian @xranthoar]

@guanlan @gaocegege @runta @a16z We really need a much better agent runtime!

[Guanlan Dai @guanlan]

Today we're announcing @runta's $20M seed, led by @a16z.
Software is constrained when you write it. Agents have to be constrained while they run.
Runta is the execution layer that controls what AI agents can actually do.

[James Xian @xranthoar]

Tool is token efficient, precise and can be governed (skill is basically tool doc).

Personal context is valuable and is what makes a difference.

Can you expose personal context and workflow as managed tools!

[James Xian @xranthoar]

@Zhifeng4cs 😍😍😍😍😍