Model Migration Python Packages

llm-preflight

Local, cross-provider preflight checks for LLM integration changes

evalshift

Open-source LLM migration and regression testing for AI agents. Compare models, detect tool-call regressions, and gate model changes in CI.

modelpin

Dependabot for AI models — replay your app's scenarios across a model migration and catch real behavioral regressions before they ship. Low false-positive by design. CLI + GitHub Action. Open-core, Apache-2.0.

evalshift-sdk

Open-source capture SDK for AI agents — records model and tool calls to build golden suites for LLM migration and regression testing.

upshift

[ARCHIVED 2026-09] An experiment in detecting and repairing AI-agent regressions across model upgrades. Development paused. Strongest result: 36/38 regressions found, 32 repaired, 4 not. MIT, runs locally.

falsifyai

Portable, content-addressed reliability evidence for LLM systems. Capture how a model behaves under perturbation; preserve, verify, and diff the evidence across model changes.

driftcut

Early-stop canary testing for LLM model migrations

modelgenius-sdk

Capture LLM call/response snapshots and validate them against the ModelGenius snapshot format — locally, with no network calls.

parity-ci

git diff for LLM behaviour. Capture what your model actually did, replay it against a candidate model, and catch what silently broke. No test authoring, no API keys required.