Squeaky Clean
Clean-Architecture codegen. Pattern-specialized. Parallelized. Cost-tiered.
An opinionated, semi-deterministic agentic framework. One declarative ProblemSpec in, a buildable, testable application out. By capitalizing on the modularity of Clean Architecture, Squeaky orchestrates atomic agents in parallel across compact, low-parameter models.
Install Get started in 5 min GitHub
What's different¶
-
Clean Architecture, top to bottom
SOLID, GoF, and DDD patterns are the shared vocabulary between agent tiers. The Dependency Rule is enforced by a real validator: domain imports nothing, application imports only domain, infrastructure implements domain ports. The framework's own source obeys every constraint it enforces on generated code.
-
Parallelized agents at compact-tier cost
Architects emit a multi-MODULE plan via the DSL, deploying one pattern-specialized atomic agent per file. By routing the vast majority of token volume to compact models — and reserving the larger tier strictly for architectural decisions — the framework builds distributed architectures in a single, high-velocity, low-cost parallel sweep.
-
Cross-service contract fidelity
Two services produce/consume the same Kafka topic? The Contract Registry enforces field-shape agreement across language boundaries with case-tolerant validation. The consumer's
ConsumedEventcarries the producer's contract field names verbatim.
Where to next¶
- Install — pip + API key + smoke test, 60 seconds.
- Get started — runnable Flask Todo API from a 40-line spec.
- Author your first ProblemSpec — walkthrough + best practices.
- Architecture deep-dive — three model tiers, parallel atomic agent fan-out, why pattern specialization matters.
- Squib grammar — the language between agent tiers.
- Agentic Architecture Recovery — coming next: brownfield round-trip into the same generation pipeline.
- Benchmarks — methodology and measured run data.