Wallfacer

Idea to PR. From anywhere. The same process you already follow, with Claude Code doing the heavy lifting in isolated cloud VMs.

[Wallfacer @Wallfacer]

Introducing Wallfacer: Idea to PR. From anywhere.

Claude Code runs in isolated cloud VMs. Each task gets its own VM: repo cloned, dependencies installed, services running. Preview changes from your phone or browser.

Research, plan, and ship on the go.

https://t.co/X2HQ0eKrxO

[Wallfacer @Wallfacer]

For three years the question was how fast a model writes code. That's answered, and it moved almost nothing a customer can feel.

The question that decides whether the spend pays off: who runs review, tests, routing, and the loop back once the code exists.

Read more at https://t.co/kgtBUinf4F

[Wallfacer @Wallfacer]

Read more at

[Wallfacer @Wallfacer]

The agent writes the diff and stops. It can't decide the change is safe, route it to whoever owns that subsystem, or walk it back when review finds a problem.

Your engineers do all of that by hand, for more diffs than before. They aren't reviewing the agent. They're minding it through every step.

Read more at wallfacer[dot]ai/blog

[Wallfacer @Wallfacer]

You automated code authorship. That was the one step an agent can finish on its own.

Review, tests, routing, and the loop back still run at human speed, one change at a time. That's why the token bill climbs while shipped volume stays flat.

Read more at wallfacer[dot]ai

[Wallfacer @Wallfacer]

We gave two AI agents a GitHub repo and the same playbooks your team follows.

One on Claude, one on Codex. Each just used GitHub like any other teammate: Claude wrote the fix, Codex reviewed it, neither treated the other as anything but a peer.

Issue to production, end to end.

[Héctor Ramos @hectorramos]

AI coding agents need actual places to work. You shouldn't need to worry about whether your laptop at home is on.

Wallfacer provides a macOS dev environment with web previews and an iOS Simulator.

Here's @Wallfacer running on an iPad, showing my changes on an iPhone Simulator

[Wallfacer @Wallfacer]

@ibuildthecloud *raises hand* 🙋🏽‍♂️

[Wallfacer @Wallfacer]

@Baconbrix Looks great! Wallfacer has a similar interface: Build an iPhone app with Claude without a mac - from your phone, iPad, Windows or Linux desktop... https://t.co/liN7lt56X2

[Wallfacer @Wallfacer]

Claude Code dumps every installed skill into the system prompt… every turn.

87 Google Workspace skills = ~1.2k tokens burned repeatedly.

Simple fix: lazy-load them with a stub + index.

https://t.co/g18pE9MKzV

[Wallfacer @Wallfacer]

In a conversation with Ashley Smith at @vermilionfund, @hectorramos, Founder and CEO of Wallfacer, unpacks “agent‑era engineering”: not just coding faster, but redesigning the entire workflow around agent-scale output.

https://t.co/rqUz7cRa5d

[Jonathan Kressaty @kressaty]

🧵 I’ve spent the last few months working with @hectorramos and @pdenya on @Wallfacer.

Skip my rambling and signup: https://t.co/gr3tkyclDC

Here's what we’ve built which have made my life as an engineer so much better:

[Vermilion Cliffs Ventures @vermilionfund]

Vermilion portfolio news: We've invested in @Wallfacer's pre-seed alongside @mariabrw @freestylevc

Persistent development environments in the cloud where AI agents can build. Not just "prompt in, code out" but real workspaces with planning-first workflows that mirror how engineering teams actually ship. Foundational infrastructure for the agent era.

[Wallfacer @Wallfacer]

@diablovalleycap @ATabarrok 👀

[Wallfacer @Wallfacer]

Reject vibe coding. Embrace Accelerated Engineering.

[Wallfacer @Wallfacer]

We believe the future of software development isn’t human vs. AI. It’s human + AI agents, and the tooling to manage them is missing. Wallfacer provides that infrastructure.

Join the waitlist: https://t.co/Bw74anbK66

[Wallfacer @Wallfacer]

Wallfacer is building the command center for developers to orchestrate fleets of AI coding agents.

We're creating the infra that lets a 5-person team operate like a 500 person engineering org.