자동화 문제가 없습니다. 당신은 결정적인 문제가 있습니다.

AI-agent 공포 이야기는 같은 방법을 끝냅니다: 행동 아무도 질문에 멈추지 않습니다. Patchwork OS는 에이전트의 임펄스와 행동 사이의 층입니다 - AI가 편집기, GitHub, Slack, Gmail 및 45 + 서비스를 통해 실제 작업을 자동화 할 수있는 로컬 첫 번째 실행 시간 **.

Who it’s for: 개발자와 기술 운영자는 이미 실제 시스템에 대한 에이전트를 실행하는 - 선박, 그 문제, 생산 서비스 - 그리고 누가 허용하고 왜 기록하려는. 터미널, 노드 설치 및 YAML 편집을 기대합니다.

세 가지 아이디어, 하나의 실행 시간 :

• ** 행동하기 전에.** 모든 행동은 폭발 반경에 의해 분류된다 - 그것은 undone이 될 수, 그리고 그것이 잘못 경우 얼마나 많은 휴식? 자유로울 수 있는 것들. 위험 한 것은 증거가 붙어있는 승인 큐에 기다립니다. 정확히 무슨 실행, 왜 그것은 화재, 그리고 그것이 잘못되면 무슨 일이 발생.

• Trust는 얻지 못했습니다. Workers — 작업과 함께 에이전트를 명명 — 감독을 시작하고 작업 유형 당 트랙 레코드에서 독립을 적립.

Patchwork OS

You don’t have an automation problem. You have a decision problem.

Every AI-agent horror story ends the same way: an action nobody stopped to question. Patchwork OS is the layer between the agent’s impulse and the action — a local-first runtime where your AI can automate real work across your editor, GitHub, Slack, Gmail, and 45+ services, while anything consequential can be made to stop and ask you first.

Who it’s for: developers and technical operators who already run agents against real systems — a repo that ships, an inbox that matters, a production service — and who want a record of what was allowed and why. It expects a terminal, a Node install, and comfort editing YAML.

Three ideas, one runtime:

• Ask before acting. Every action is classified by blast radius — can it be undone, and how much breaks if it’s wrong? Reversible things flow freely. Risky things wait in an approval queue with the evidence attached: what exactly will run, why it fired, and what happens if it’s wrong.

• Trust is earned, never assumed. Workers — named agents with jobs — start supervised and earn independence from their track record, per action type. Good at filing issues ≠ allowed to push code. One bad high-stakes action outweighs a hundred trivial successes. You set the ceiling; the math never raises it for them.

• Every decision leaves a receipt. What was done, why it was allowed, and how it turned out — durable, replayable, explainable via patchwork judgments, the dashboard’s traces page, and patchwork gate explain. When you approve something, you find out later whether you were right.

An agent wants to write a file. With the gate on, it waits — and shows you exactly what it would do:

You approve. The call proceeds, and both halves are on the record:

Status: stable 1.2

Version 1.2.6, published to npm as latest. The decision layer, recipes, connectors and IDE bridge all work and are dogfooded daily. Interfaces can still change between minor versions and some surfaces are rougher than others. Pin an exact version if you are building on it.