zechenzhangAGI

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring.

Multi-cloud orchestration for ML workloads with automatic cost optimization.

Autonomous AI agent platform for building and deploying continuous agents.

Open-source embedding database for AI applications.

Fast tokenizers optimized for research and production.

Reserved and on-demand GPU cloud instances for ML training and inference.

LLM observability platform for tracing, evaluation, and monitoring.

Serverless GPU cloud platform for running ML workloads.

High-performance vector similarity search engine for RAG and semantic search.

Distributed training orchestration across clusters.

Foundation model for image segmentation with zero-shot transfer.