Code scanner to check for issues in prompts and LLM calls

Turbocharged TensorFlow fork with experimental TurboQuant extension. High-performance weight-only, block-wise codebook quantization for Keras layers.

A functionally operational, mathematically unhinged system for achieving 10× effective memory amplification on Apple Silicon using quantized fractal compression, complex-plane KV decomposition, and Euler-aligned swap geometry.

Building an AI team to play Codenames using top Large Language Models (LLMs), evaluating performance, and pitting them against each other. Explore their strategy and capabilities in this interactive competition!

Arbitrary Numbers

La Perf is a framework for AI performance benchmarking — covering LLMs, VLMs, embeddings, with power-metrics collection.

KAI Data Center Builder

Powerful AI efficiency tool that reduces token usage by up to 75% for cloud code and LLM applications. Ideal for developers looking to maximize performance while minimizing costs in 2026.

Test AI provider latency (TTFB, TTFT, TPS) in your CI/CD pipeline. Benchmark OpenAI, Anthropic, Google, and more.

AI Performance Engineering Cheatsheet: From Cloud to Edge.

Chrome extension that removes old ChatGPT messages from the DOM to keep long conversations fast and responsive.

A streamlined and easy-to-use AI performance evaluation / summary template with modern UI in HTML, including correct percentage chart and comparison with other models, precision, recall, F1-score, and confusion matrix. Enables you to create the result chart within 3 minutes.

Correctness-first microbenchmarks for LLM attention and sampling kernels.

Speedtest for AI. Test latency to every major AI provider from your terminal.