Mergekit Python Packages

crdt-merge

Mathematically proven conflict-free merge for AI model weights, datasets, and agent memory with recursive trust-delta entanglement. Zero dependencies. Patent protected.

mergelens

Pre-merge diagnostics for LLM model merging

rho-eval

Behavioral auditing toolkit for LLMs — audit any model across 8 dimensions (factual, toxicity, bias, sycophancy, reasoning, refusal, deception, over-refusal) using teacher-forced confidence probes.

layer-scan

Automated LLM layer duplication config scanner

knowledge-fidelity

Compress LLMs while auditing whether they still know truth vs myths. SVD compression + false-belief detection in one toolkit.