Industrial-strength NLP library for Python with pre-trained pipelines for tokenization, NER, parsing, and more.

Run PyTorch training scripts on any hardware — single GPU, multi-GPU, TPU — with minimal code changes.

Instant voice cloning with precise style control — tone, emotion, accent, and rhythm from a single short reference clip.

Microsoft's deep learning optimization library — train trillion-parameter models with ZeRO memory parallelism.

CTranslate2-powered reimplementation of Whisper with up to 4× faster inference and lower memory usage.

Meta's Segment Anything Model 2 — real-time promptable segmentation for images and videos with streaming memory.

Apache-2.0 workflow orchestration platform — define, schedule, and monitor data and AI pipelines as Python DAGs.

8-bit and 4-bit quantization for PyTorch — run and fine-tune LLMs on consumer GPUs with minimal quality loss.

Blazing-fast DataFrame library written in Rust with a Python API — handles datasets that don't fit in RAM.

Industrial-grade multilingual OCR toolkit supporting 80+ languages with text detection, recognition, and layout analysis.

Fine-tune LLMs with RLHF, PPO, DPO, SFT, and GRPO — the standard library for aligning language models.

OpenAI's lightweight Python framework for building multi-agent systems with handoffs, tracing, and guardrails.

Google's on-device ML framework for face, hand, pose, and object detection across mobile, desktop, web, and edge.

Production-grade Stable Diffusion studio with a node-based workflow editor, ControlNet, IP-Adapter, and full REST API.

Unified fine-tuning framework for 100+ LLMs — SFT, RLHF, DPO, LoRA, QLoRA via Web UI or CLI.

Open-source durable execution platform for building reliable distributed workflows and long-running processes.

Meta AI's promptable image segmentation model that can segment any object from a single click or bounding box.

Apache-licensed 7B language model from Mistral AI — beats Llama 2 13B on most benchmarks at half the size.

ProjectDiscovery's fast, template-driven vulnerability scanner with 9,000+ community templates for web apps, APIs, cloud, and AI service endpoints.

Pioneering autonomous task-management AI that uses GPT-4 and vector memory to self-generate and prioritize tasks.

Lightweight neural voice activity detector that distinguishes speech from silence/noise in real time.

Princeton's autonomous agent that resolves real GitHub issues end-to-end using a custom agent-computer interface.

Open-source vector similarity search for PostgreSQL — store and query embeddings directly in your Postgres DB.

One-line OCR for 80+ languages including Latin, Chinese, Arabic, Devanagari, and Cyrillic — no training required.