Frameworks, SDKs, and infrastructure for building AI applications.
Meta's open-weight instruction-following model. Available in 8B and 70B parameter sizes.
Visual IDE for building AI agents and RAG workflows. Drag-and-drop interface on top of LangChain wit…
Pure C/C++ implementation of LLM inference. No dependencies, runs on CPU and GPU with quantization s…
Composable building blocks for LLM-powered agents with tool use and memory.
OpenAI's multilingual speech recognition model. Accurate transcription across 99 languages.
High-throughput, memory-efficient LLM inference engine. Supports PagedAttention, continuous batching…
Run open-source LLMs locally on your machine. Llama 3, Mistral, Phi3, and more with one command.
Lightning-fast search engine API with AI-powered hybrid search (BM25 + vector). Sub-50ms responses, …
Port of OpenAI Whisper to pure C/C++. CPU-first with optional GPU acceleration. Works on Mac, Linux,…
Leading document agent and RAG framework for LLMs. Connect your data to GPT-4, Claude, and local mod…
All-in-one web UI for running open-source LLMs locally. Text, vision, tool-calling, OpenAI-compatibl…
Hugging Face library for state-of-the-art diffusion models. Image, video, and audio generation in Py…
Build resilient, stateful multi-agent applications. Extends LangChain with cycles, memory, and fault…
Open-source LLM engineering platform. Traces, evals, prompt management, playground, and datasets. In…
The AI Toolkit for TypeScript. Streaming, retries, and UI primitives for React, Svelte, Vue, and Nod…
The AI-native open-source embedding database. Fast vector similarity search with built-in query capa…
Unified interface for 100+ LLMs. Call OpenAI, Anthropic, Azure, Gemini, and local models with one AP…
The LLM evaluation framework. Pytest-like unit tests for LLMs with hallucination detection, RAG eval…
Framework for evaluating RAG pipelines. Faithfulness, answer relevancy, context precision, and citat…
A platform for running open-source AI models via API. Run Stable Diffusion, FLUX, CogVideoX, and mor…
Unified fine-tuning framework for open LLMs. Supports QLoRA, full-parameter, multi-node training and…
Developer-friendly embedded vector database for multimodal AI. No server required, designed for prod…
Reliable event-driven serverless functions. Use AI in production without managing infrastructure.
Hosted inference API for the best open-source models. Finetuning and function calling support.
Build natural language interfaces using types. Type-safe LLM output parsing with schema validation, …
Enterprise AI platform with embedding models, rerank, and command models via API.