Subspace is built from the ground up for **AI-native product development**

If you like us spend most of your day working with Claude Code, Codex, OpenCode, or other CLI Agents, we think you will love Subspace.

subspace.build

As Subspace evolved, the old tools stopped working entirely.

And after using Subspace daily for the last few months, it’s now impossible to imagine building products without it.

So we had to ship it.

Subspace wasn’t planned as a product.

It emerged from solving our own friction points — prompts, workflows, context, parallel work, orchestration, memory, prioritization — where each solution exposed the next problem.

Working with them 10+ hours a day made one thing clear:

both the agents **and the humans operating them** are bottlenecked by tools designed for a completely different era.

They were never built for sustained and multi-threaded human–agent collaboration.

While building @newjunehq, we've fully embraced agentic engineering and tools like Claude Code and Codex.

The plan from the start was to be fully AI native from the start.

Coding agents are _insanely_ capable.

but ...

www.subspace.build

No scale.

If that was measurable, and thus every skill/subagent/workflow was empirically improveable…

Many of the diehards figured this out long ago - long running markdown task lists and session handoff/resume workflows are must haves.

www.anthropic.com/engineering...

Before Sonnet 4.1 could get pretty far on a feature idea/prototype but it would be a mess of code and take lots to get it working.

Opus 4.5 just gets you closer, and that is enough to be completely game-changing.

The "work" is starting to shift more heavily to project/product management.

• When something doesn't work - summarize learnings and try again.
• When it works, small amount of iteration to get it completely ready to ship

The amount of complex work that I've completed this week with Opus 4.5 is profound relative to where we were literally days ago.

The big change for me has been

• Opus can easily get 85-100% right on almost any prototype/feature idea I have, so its insanely cheap to try LOTS of new things.

I can’t afford to be locked in CC or Codex or even an agent agnostic tool like Factory or Opencode or Amp, and I can’t afford for every future employee to start “behind” relative to myself or my cofounder in terms of tools, skills, prompts, MCPs, you name it.

For my cofounder and future employees - I want to control the defaults, ensuring that we have the flexibility and the system set up to make anyone 10x from day one.

Right now, how good you are with Agentic Coding is a function of your obsession with finding/using/experimenting with all the tools.

1. speed - being able to use the *best* coding agent and model at any time to deliver more results faster

2. quality - using the best available tools (and powerful zero config defaults) at all times to ensure highest quality AI output