A local control plane for AI-assisted software development. No magic-from-a-socket — instead a structured production line of wizard, supervised runs, Git discipline and an automatic quality gate. Reproducible, traceable, sign-off-able.
New · v0.42.1
Better .NET support: the sandbox builds with the SDK that matches the project (global.json
or TargetFramework), the agent may call dotnet itself, and the wizard suggests
.NET 10 with 9 and 8 selectable. Also new: a trial version with an expiry date and no license file.
Before that, v0.42.0 brought the tester package: license as a file, costs live and estimated
before the start, C# in the container sandbox and a starter package.
All news →
The six-step wizard only asks what's needed for a concrete
project: target platform, backend, frontend(s), stack-specific
questions, quality-gate toggles, summary. 18 templates —
five backends from Spring Boot to FastAPI, twelve frontends from
React to JavaFX, plus importing an existing repository. The
result: PROJECT.md, AGENTS.md and an
initial prompt you can preview before starting.
Run orchestration with live logs, token and cost tracking and
container sandbox. Build and scans run with hard limits
(--cpus 2 --memory 4g --read-only), the agent writes
only to the workspace, 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.
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. 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.
