You describe an application in your own words, AI agents such as Claude Code build it, the factory checks the result — and you approve. Behind it is a local control plane with supervised runs, Git discipline and an automatic quality check: reproducible, traceable, sign-off-able.
New · v0.52.7 The guided path: initial setup in three steps with a system check, describe your project in the quick start and click "Bauen" (build) — for existing projects too —, a run page that refreshes itself, and the result as a ZIP with a start command. Runs work in the background; "Einfach | Experte" sets how much you see. All news →
You say in your own words what should be built — three inputs in the quickstart are enough, an existing project comes in via folder or Git address. The factory turns this into a clear task for the agent that you can read and change before the start. If you want to choose stack and checking tools yourself, use the detailed wizard with templates.
Runs work in the background; the run page shows progress, "Was
jetzt?" (what now?) and the one button you need right now. Live
logs, token and cost tracking and container sandbox. Build and scans run with hard limits
(--cpus 2 --memory 4g --read-only by default, adjustable per project), the agent works
in the project workspace (as a program on your machine, not in the container), every change is a commit. Browser
notification when you need to make a decision.
Inline diff before every approval. Automatic quality gate from seven reviewer roles — Security, Architecture, Hallucination, dependency scan, spec conformance (only for runs with a spec), plus two vendor reviewers. No "Approve / Reject" blind flight, but findings split into blocking and advisory, with a confidence score per reviewer.
Click through a real instance without installing anything and without an account — with a guided tour.
Request the starter package, do your first run at no cost in the quickstart, then connect your subscription or API key.
Tenants, roles, SSO, a signed audit chain and policy-as-code — Cloud, Self-Hosted or Air-Gap.
free
For a single seat. No account, just an e-mail address; the factory fetches the license itself.
€20–30/month
Per user. Higher limits, spec-driven development, priority support.
from €20,000/year
Contracted limits, SDD governance, Cloud, Self-Hosted or Air-Gap.
You pay for the AI models directly to the provider. All limits and lease durations: Pricing →
Reference architecture, agent orchestration, guardrails and SDLC integration — as an architecture document, not a tool comparison. If you want to know why the factory is cut this way, start here.
Coding agents are already good at solving individual problems. They are bad at sticking to structure, cutting commits sensibly, getting reviews and checking their own output. The Software Factory takes those steps over — not the creative part.
The result: AI-assisted development that an architect can hand to a client without cleaning up the trail afterwards.
With Claude Code, the Architect gets Opus by default, the Developer Sonnet, the Reviewer the lean, fast Haiku — saving tokens where quality isn't hurt and giving the strong model to the strategic roles. The mapping comes from the model catalog, can be overridden per team or via settings and is updated with factory releases.
Before every run the platform writes
.claude/settings.local.json and
.claude/agents/<role>.md into
the workspace. With the Claude Code project context
switched on for the project, subagents are natively
delegable without touching the CLI.
Optional: build and scans of the generated
project run in an ephemeral Docker container
with hard limits and a --read-only
root, only the workspace is mounted. The agent
itself runs with an ephemeral HOME free of
foreign configuration.
At WAITING_FOR_APPROVAL the platform
shows the final git diff. You see what
the agent changed before you press the button.
The wizard summary shows a token and EUR estimate — before the first run, without a vendor call. JTokkit computes locally.
Software architect with over three decades between mainframe (z/OS, Cobol, REXX) and cloud (Java/Spring, AWS, Azure, Kubernetes, microservices). In the frontend with Apache Wicket and Angular, in mobile founder of a German-speaking Xamarin community.
Certifications (selection): CKAD — Certified Kubernetes Application Developer (CNCF), AWS Certified Cloud Practitioner, Microsoft Certified: Azure Fundamentals (AZ-900), iSAQB CPSA-F (software architecture) and Oracle Certified Professional 12c.
The Agentic Software Factory is my attempt to embed AI agents into the software lifecycle in a way that makes them productive even under mid-market and compliance constraints — structured, traceable, sign-off-able rather than blindly generated.
