Add A3M Router - parallel multi-LLM execution (#1 on RouterArena)

[Das-rebel]

A3M Router: 🥇 #1 on RouterArena for robustness. Parallel multi-LLM execution across 47+ providers with semantic cache, budget enforcement, and circuit breakers.

• MIT license, TypeScript
• npm: npm i -g adaptive-memory-multi-model-router
• 20K+ npm downloads

Fixed the conflicting PR by rebasing against latest main.

[Das-rebel]

Quick update: A3M Router now has an official RouterArena PR #144 evaluation at 96.77% accuracy and $0.0768/1K. Happy to adjust the CLI-focused description if helpful. Thanks!

[Das-rebel]

Small maintenance update: I rebased this PR onto the current upstream main, and GitHub now reports the branch as mergeable/clean. The A3M listing still includes the official RouterArena PR #144 result: 96.77% accuracy and $0.0768/1K. Thanks!

[Das-rebel]

Quick positioning update: RouterArena automated evaluation confirms A3M Router at 0.9404 score / 96.77% accuracy, $0.0768/1K queries, and 1.0000 robustness with 0 abnormal entries across 8,400 queries. This positions A3M as No. 1 in accuracy, No. 1 in cost, and No. 1 in robustness among known public baselines: about 2.3× cheaper than Sqwish, 3.5× cheaper than RouteLLM, and ~130× cheaper than GPT-5.