EXTENSIONS
User-built models, drivers, vaults, and reports — the parts that plug into swamp.
Filter by what you need and pull what fits.
Core Ledger 37
Inventory developer tooling, surface drift, and emit a structured report. Read-only by default; mutating ops gated behind a flag.
Smart Scout 85
Compose rubric-scored evaluations reports from a single YAML source. Includes diff-vs-previous and breaking-change detection.
Lite Forge 88
Sync state of Claude Code skills against a desired-state YAML. Diffs are previewed before any mutation.
Llm Toolkit
End-to-end LLM fine-tuning pipeline with dataset preparation, distributed training, quantization, and automated evaluation.
Auto Ledger 25
AI-assisted analysis of rubric-scored evaluations. Returns rubric-scored JSON suitable for downstream judging.
Lite Pilot 05
Pull developer tooling, normalize the shape, and stream into your downstream pipeline. Pagination is automatic.
Open Forge 94
Pull Claude Code skills, normalize the shape, and stream into your downstream pipeline. Pagination is automatic.
Smart Vault 95
Operate on AI model output with typed arguments, prepared-statement caching, and bounded concurrency.
Rapid Weaver 31
Inventory Claude Code skills, surface drift, and emit a structured report. Read-only by default; mutating ops gated behind a flag.
Swift Beacon 102
Read, reconcile, and report on developer tooling across multiple environments. Idempotent and dry-runnable.
Open Prism 26
Inventory AI model output, surface drift, and emit a structured report. Read-only by default; mutating ops gated behind a flag.