Guanlan Dai

Building @Runta, the execution layer that controls what AI agents can actually do. Prev @Cloudflare and @Kong.

[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.

[Guanlan Dai @guanlan]

@quinn_leng We need a company harness!

[Runta @runta]

Runta 10/10/2026 is now available!

Resize on cold checkpoint restore. Restore a cold checkpoint with a different CPU and memory shape, so you can scale the runtime without rebuilding its environment.

Smoother runtime creation at scale. Improved batching, scheduling, and higher API limits help runtime creation stay responsive during bursts.

Simpler ChatGPT subscription setup. New runtimes use your account’s default model, while unavailable subscriptions stay hidden.

[Guanlan Dai @guanlan]

@thedavidqu great use case

[Guanlan Dai @guanlan]

Pi 1.0 runs on Runta today.

Each agent gets its own machine: hands-on in a browser terminal, or headless over an API with live streaming, steering, and cancel. Pi never sees your real keys.

Our egress layer swaps in model and credentials on the way out.

[Guanlan Dai @guanlan]

Give it a try for free:
https://t.co/j9ZCs1VDUu

[Guanlan Dai @guanlan]

@KakaluoteW45042 We think benchmark each harness with its own default configuration is a better fit, it lets each harness lean into its own strengths.

[Guanlan Dai @guanlan]

FrontierHarness v1.1 is coming.

We're putting together an expert advisory group with maintainers of well-known coding-agent harnesses, plus related researchers from Stanford, Berkeley, and Caltech. A top-tier inference partner is also ready to sponsor the next eval runs.

In v1.1 we'll cover more models, more harnesses, and a more representative task set. Expect an order-of-magnitude jump in both run count and tokens used, so the harness × model picture gets clearer.

More soon.

[Guanlan Dai @guanlan]

@JamesNguyen868 @AmpCode @Empryo_ai will look into this

[Guanlan Dai @guanlan]

@maxintechnology Compaction is crucial

[Guanlan Dai @guanlan]

@yifanxu_ephai We are actively hiring, would love to chat.

[Guanlan Dai @guanlan]

Full teardown here, including how Muse's Sentinel checks requests even after a command is already running: https://t.co/gqtwEsZBHo

[Guanlan Dai @guanlan]

Your agent doesn't need to escape the sandbox to leak your files.

It just needs to run curl.

We looked inside Grok Bot and Muse to answer one question: what happens after the injection lands?

Our take: command review isn't enough. The check belongs at the exit, run by something the agent can't turn off.

[Edward @edward40e]

Want to be part of the FrontierHarness Eval initiative?

v1.0 covered 1 model × 12 harnesses. Next for v1.1: 5 models × 20 harness configurations.

Explore https://t.co/FJqPgbGyMj. Reply to this post and I’ll invite you to the channel. Feedback welcome!

[Tyler Mayberry @tylermayberry]

This is the most important bench at the moment @runta

https://t.co/twA8WUHq7B

[Guanlan Dai @guanlan]

@edward40e One of the reasons is copyright: for some open source, you have to sign certain CLA to be able to contribute

[Guanlan Dai @guanlan]

Blog post on how he built it:
https://t.co/inJG9Ktgrj

[Guanlan Dai @guanlan]

One of our engineers built Errand, our open-source take on Grok Bot and Muse, and wrote up how it came together. One developer, one week.

The app is ~4k lines of TS. Every agent still gets its own machine with a shell, a browser, and a filesystem that survives between tasks. He never wrote a provisioner or an event log infra.

If you're about to build this layer yourself, that's what Runta is. Week one goes into your product instead of a provisioner.

I'd like to hear where you're stuck, if you're in the middle of it right now.

[Shiqi @heyshiqi]

Your Jev can actually speak. Introducing Jot, The first general-purpose System One agent for Jev.

[Guanlan Dai @guanlan]

@abdolamunir Both of them looks great, Errand has the features that build-in from Runta Infra: the tracing, credential handling, networking policy, checkpoints and token saving.

[Guanlan Dai @guanlan]

Grok Bot and Muse are great. We built an open-source version and called it Errand.

Hand it a task, close the laptop, come back in the morning.

[Guanlan Dai @guanlan]

@dragonofllms not yet, local VM sounds great