Source code for the paper "Accelerating Hierarchical Federated Learning under Mobility via Model Migration in Cloud–Edge–End Collaborative Networks".

Migrate LLM apps between models safely — then benchmark old vs. new to prove the upgrade. Agent skill for behavior-preserving migrations + a runnable eval harness (three-arm leaderboard, prompt sweeps). Works in Claude Code, Codex & Cursor.

Early-stop canary testing for LLM model migrations

A portable memory skill and CLI for AI agents: curated context, user preferences, topic interruptions, handoff packets, and model/runtime migration without transcript dumps.

Why a passing benchmark isn't safe to ship: a free 2-stage (benchmark + replay) validation recipe for LLM model swaps & prompt changes, run on flat-rate coding-agent subagents — no eval API bill.

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.

Cut LLM/inference cost of any GenAI app: migrate an expensive model to a cheaper one without quality loss via a deep adversarial test suite + oracle/student prompt-optimization loop. A Claude Code skill.

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