Vorflux has opened public sign-ups for a cloud platform that takes a software task from intent to a merged pull request without a laptop staying in the loop. The company positions the product as an autopilot for software engineering: a session starts from what Vorflux describes as two links and a sentence, then covers planning, building, testing, review, and the merge itself, with the person who filed the task approving by exception. Sign-up is live on Vorflux's website, and the Vorflux team configures larger setups in collaboration with the customer.

The machine is what separates it from a cloud sandbox. Each session spins up an entire stack on a dedicated EC2 instance, cloning repos, installing libraries, and bringing up frontend, backend, mobile services, and databases, with CI/CD, feature flags, and environment variables wired in. Vorflux then snapshots the box with everything live, so later sessions wake on a computer that is already running. Because the application genuinely runs, a testing pass can drive a browser through the real user flow, record it, and attach that recording to the pull request as proof. A phone boots in the cloud for native tests, and every branch gets a live URL for review before merge.
Circle the bug. Send an-inline request to Vorflux. Get back a PR with proof it's fixed. pic.twitter.com/Pf3Ru1qyY6
— Vorflux (@vorfluxai) August 11, 2026
Vorflux trains none of its own models and routes each stage to whichever frontier model leads that job, covering Claude, GPT, Gemini, and open-weight options. Planning receives the largest token budget, expanding intent into a plan of sub-tasks, each with its own test cases, with a model from a separate lab critiquing the draft before code is written. The same cross-lab logic runs at review, where a reviewer outside the author model's family grades the diff and retells it in plain language with the most important change first. A merge queue then handles rebases and conflicts against a moving master.
Ask why prod is slow. Get back a diagram of exactly where pic.twitter.com/qoB5mj6ETn
— Vorflux (@vorfluxai) August 6, 2026
Billing splits three ways:
- Customer provider keys paid directly.
- Tokens bought through Vorflux at standard provider rates with no platform fee.
- An existing Codex subscription routed in under an OpenAI partnership.
Compute runs hourly, from roughly 21 cents for a 2 vCPU box up to 3.39 dollars for 32 vCPUs, and servers auto-stop after an hour of idle time. A white-glove tier embeds a Vorflux engineer who runs the agents against the customer backlog and ships verified pull requests weekly.
Start testing Vorflux
Vorflux was founded by Prasanna Sankar, co-founder and former chief technology officer of Rippling, and launched in July 2026 with funding from Y Combinator, Peak XV Partners, Powerset, and Alliance, alongside angels including Parker Conrad, Immad Akhund, and Balaji Srinivasan. Sankar has framed human time, not tokens, as the remaining bottleneck in software delivery, and the company builds around a layer it calls the harness: the place where a team encodes its own engineering standards so they run on every session. The stated target is technical founders, CTOs, and engineering leaders carrying review backlogs and testing debt.