Giovanni Pasqualino

ruff. An extremely fast Python linter and code formatter, written in Rust.

langflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

liteparse. A fast, helpful, and open-source document parser

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

dspy. DSPy: The framework for programming—not prompting—language models

brew. 🍺 The Package Manager for Everywhere

markdown-pdf. Markdown to pdf renderer

xberg. A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

llama.cpp. LLM inference in C/C++

unsloth. Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

presidio. An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

markitdown. Python tool for converting files and office documents to Markdown.

langfuse. 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

chunky. Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

Qwen3-ASR. Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

awesome-LangGraph. An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps.

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

langextract. A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

hyde. HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

fastapi. FastAPI framework, high performance, easy to learn, fast to code, ready for production

tokenizers. 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

pandas-ai. Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

chonkie. 🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

deepeval. The LLM Evaluation Framework

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

PyMuPDF. PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

pymupdf4llm. PyMuPDF4LLM

Qwen3-Embedding. Python

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

uv. An extremely fast Python package and project manager, written in Rust.

unstructured. Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

DeepSeek-OCR. Contexts Optical Compression

ragas. Supercharge Your LLM Application Evaluations 🚀

KeyBERT. Minimal keyword extraction with BERT

ollama-python. Ollama Python library

LupusInFabula_Datapizza_AI. Autonomous AI simulation of Lupus in Fabula (Werewolf/Mafia) with secret roles, narrative storytelling, and strategic player planning.

agentic-rag-for-dummies. A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Kimi-K2. Kimi K2 is the large language model series developed by Moonshot AI team

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

docling. Get your documents ready for gen AI

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

Medusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

guardrails. Adding guardrails to large language models.

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

pydantic. Data validation using Python type hints

vision. Datasets, Transforms and Models specific to Computer Vision

trl. Train transformer language models with reinforcement learning.

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

langgraph. Build resilient agents.

suricata. Type-safe AI agents for Go. Suricata combines LLM intelligence with Go’s strong typing, declarative YAML specs, and code generation to build safe, maintainable, and production-ready AI agents.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

flux. Official inference repo for FLUX.1 models

autogen. A programming framework for agentic AI

nanoVLM. The simplest, fastest repository for training/finetuning small-sized VLMs.

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

optuna. A hyperparameter optimization framework

BERTopic. Leveraging BERT and c-TF-IDF to create easily interpretable topics.

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

langchain. The agent engineering platform.

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

digler. Digler is a tool for forensic disk analysis and file recovery. It's designed to help you unearth lost or deleted data from various disk images and raw devices.

proq. 🚀 proq – An embedded in-memory Prometheus server with real-time terminal plots & histograms. Ideal for debugging without a full Prometheus setup.

MITS-GAN. Official implementation of MITS-GAN: Safeguarding Medical Imaging from Tampering with Generative Adversarial Networks, Computers in Biology and Medicine (CBM) 2024

kronos. A lightweight cron job scheduler with webhook notifications, designed for easy task automation and flexible scheduling

zipcache. An in-memory compressed cache for gigabytes of data written in Go.

torchmetrics. Machine learning metrics for distributed, scalable PyTorch applications.

lightning-flash. Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains

vis-network. :dizzy: Display dynamic, automatically organised, customizable network views.

aos. Animate on scroll library

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

xdcc-cli. A command line tool for searching and downloading files from the IRC network.

pytorchvideo. A deep learning library for video understanding research.

clover. A lightweight document-oriented NoSQL database written in pure Golang.

DA-Faster-RCNN. Detectron2 implementation of DA-Faster R-CNN, Domain Adaptive Faster R-CNN for Object Detection in the Wild, Computer Vision and Pattern Recognition (CVPR) 2018

Fast-Insertion-Sort. C++

eagle. A fast and strongly encrypted key-value store written in pure Golang.

viperdb. A tiny log-structured key-value database written in pure Python.

STMDA-RetinaNet. Official Detectron2 implementation of STMDA-RetinaNet, A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training, Computer Vision and Image Understanding (CVIU) 2022

unique-factor-matcher. C

DA-RetinaNet. Official Detectron2 implementation of DA-RetinaNet, An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites, Image and Vision Computing (IMAVIS) 2021