Runta

The execution layer to control what AI agents can do as they run.

[Runta @runta]

If you're trying to give agents real work and control is what's stopping you, apply for early access today.

Every new account starts with $50 in free credits, enough to run an agent for a month, with no credit card needed.

[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.

[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.

[Runta @runta]

Pi 1.0 harness support is ready at Runta. Code-mode + native MCP is finally here:

[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]

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]

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.

[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.

[Runta @runta]

@tylermayberry And we’re just getting started, something even more exciting is coming.

[Tyler Mayberry @tylermayberry]

This is the most important bench at the moment @runta

https://t.co/twA8WUHq7B

[Runta @runta]

This is exactly why we built Runta: so teams can spend their time building the agent experience, not rebuilding runtimes, computer use, persistence, and execution infrastructure. Errand is what that leverage looks like: one developer, one week, and an open-source product you can try today.

[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.

[Guanlan Dai @guanlan]

We made a little film for Errand. Cost us about $10.

Someday errands will run themselves. Enjoy.

[Runta @runta]

@guanlan One developer, one week, a full AI teammate with its own computer. That's what a real execution layer makes possible. Check out Errand!

[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.

[Runta @runta]

EXO harness support is ready. Self-evolve started!

[Edward @edward40e]

A cool thing is that you can use Runta to have exo agent play The Legend of Zelda: Link's Awakening

[Runta @runta]

A harness that rewrites itself needs somewhere scalable and safe to do it.

Exo Harness now runs natively on Runta.

[Guanlan Dai @guanlan]

Exo Harness now runs natively on Runta.

In FrontierHarness Eval, Exo was cheapest per completed task at $1.05. On the hardest task it hit its 51-step cap and quit at $1.46 while others kept spending.

That is the harness you let rewrite itself. Exo's Executor holds no durable state, so the agent can modify it. History, artifacts, secrets and sandbox lifecycle sit in the Harness, out of reach.

Runta provides a resumable environment, so the Exo Harness can self-evolve freely. Exo never holds the model API key, only a stub. Our egress gateway injects the real one at the provider. Code the agent wrote can read whatever the Executor can, and all the Executor has is a stub.

[Hacker News 20 @betterhn20]

Show HN: FrontierHarness Eval – 9 harness, same model, cost per pass varies 17x https://t.co/ki2s5g2YRO (https://t.co/uL6VSBzj3j)

[Rach @rachpradhan]

really cool benchmark!! and amazing work @guanlan!!

I was looking for a way to benchmark my own harness too and it was hard to quantify what's a good harness!!

I did run the experiment with graff, and here are the results!!

(would love to collab on things if you're free!)

[Runta @runta]

BYOH (Bring your own Harness) is supported in FrontierHarness, 1 prompt to setup the whole runtime environment to eval your own harness.

[Guanlan Dai @guanlan]

Wondering where your harness would land on the FrontierHarness leaderboard?

Last week the most common reply was "can I run mine on this."

Now you can.

Bring your harness and your own model key, and it runs on Runta under the exact conditions the leaderboard was built on: same gateway, every run a fresh restore of the same golden checkpoint, memory state included.

See where your harness actually lands next to the rest of the field.

Send us the run, and if it stands out we'll include it in the next official round.

[Guanlan Dai @guanlan]

Front page of HN, 1700+ posts on X.

Turns out a lot of people have been wondering what the harness layer actually costs , and whether the expensive ones are any better.

The harness war is on.

[Thomas Wolf @Thom_Wolf]

@guanlan Great work Guanlan!