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.

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.

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.

Try EXO on Runta under 2 mins with $50 free credit. runta.com/blog/introducing-e…

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.

Remarkable result for Exo, best price / performance. Exo's design philosophy is to expose the full harness code to the model for self improvement to be maximally bitter lesson aligned. Not just the prompt, but the entire running code and logs with ability to upgrade dynamically.

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.

v1.0 focused on software engineering and terminal tasks. Next we will test the full harness × model grid. Much of what we observed points to harness-model fit rather than harness quality, and we want to identify which combinations maximize pass rates while minimizing cost. Leaderboard and the long version: frontierharness.org/

Spent the morning in dsh (@deepseek_ai Harness). The underrated part is that sessions are an append-only log of everything the model saw. That does not give you replay of authority: what credentials the task held, what it could reach, what it could write. We are making dsh run on Runta to fix this.