Open Factory

open-factory

[](https://github.com/itsmekeyan/open-factory/actions/workflows/ci.yml) [](https://github.com/itsmekeyan/open-factory/releases/latest) [](LICENSE)

**Open Factory is a harness-agnostic toolkit for running ambitious agent workflows reliably across coding agents.** Its first product is [Lauren Tan (@poteto)](https://x.com/poteto)'s [pstack](https://github.com/cursor/plugins/tree/main/pstack) — the skills she uses to ship code at Cursor — re-engineered so the runtime and model-dispatch layer is portable across Cursor, Claude Code, and Codex. The factory is built to grow: pstack is the first product in it, and the architecture keeps planning and state harness-neutral so more products can be layered on top.

Lauren built pstack from the skills she uses to ship code at Cursor. In a [55-minute interview with Denis Labelle](https://x.com/DenisLabelle/status/2091337807939706928), she says that she shipped 1,000 pull requests in one month after steadily improving how her agents work and verify their results.

If you want to go fast, go deep first.

The first product: pstack

pstack is not a new model or a hosted service. It gives your agent engineering rules, step-by-step workflows, focused skills, and small local tools. The normal entry point is `poteto-mode`. You give it a task in plain language. It then:

• reads the task and chooses a workflow that fits;
• learns how the current system works before changing it;
• compares designs when the choice matters;
• favors small, simple changes over extra machinery;
• asks several models to challenge important decisions when useful;
• runs the code and checks real behavior instead of stopping at “the tests pass”; and
• carries the work through review, continuous integratio