Explore Data & AI Tools
Search and filter structured profiles for 337 data and AI technologies. Compare pricing, deployment models, architecture fit, public adoption signals, alternatives, and related stack components.
Search and filter structured profiles for 337 data and AI technologies. Compare pricing, deployment models, architecture fit, public adoption signals, alternatives, and related stack components.
Self-hosted open runtime that speaks the OpenAI, Anthropic, Ollama, and ElevenLabs APIs, running text, voice, vision, image, video, and agent workloads on your own hardware — CPU-only included.
Self-hosted runtime for open-weight models — pulls and serves chat, coding, vision, and embedding models on macOS, Linux, Windows, or Docker behind OpenAI- and Anthropic-compatible APIs.
Serving runtime for large language and vision models built around RadixAttention prefix caching, a zero-overhead batch scheduler and structured-output decoding, behind an OpenAI-compatible API.
NVIDIA's inference engine for large language models — compiles a model into an optimised TensorRT runtime with in-flight batching, paged KV caching and FP8/FP4 quantisation, tuned for NVIDIA GPUs and nothing else.
High-throughput inference and serving engine for LLMs — PagedAttention, continuous batching, and tensor/pipeline parallelism keep GPUs saturated across concurrent callers, behind an OpenAI-compatible API.