Awesome Opensource Ai

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

The official CLI and Python client for the Hugging Face Hub.

Simple RL training for reasoning

Superfast AI decision making and intelligent processing of multi-modal data.

A library for mechanistic interpretability of GPT-style language models

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Generative models for conditional audio generation

Open-source security automation platform for teams and AI agents

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

The best OSS video generation models, created by Genmo

Open-source multimodal retrieval engine (Morphik Core)

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Quickly and accurately render even the largest data.

Synthetic data generation for tabular data

Evaluation and Tracking for LLM Experiments and AI Agents

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Build production-ready AI agents in both Python and Typescript.

II-Agent: a new open-source framework to build and deploy intelligent agents

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Scalable and efficient data transformation framework - backwards compatible with dbt.

JAX-based neural network library

Dead simple FLUX LoRA training UI with LOW VRAM support

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

The Security Toolkit for LLM Interactions

OneTrainer is a one-stop solution for all your Diffusion training needs.

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Playwright that anti-bots cannot see, so no captchas: same API, anti-detect stealth headless Firefox, undetected fingerprint, bypass bot detection, Python web scraping and browser automation.

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Visualize and compare datasets, target values and associations, with one line of code.

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

A framework for prompt tuning using Intent-based Prompt Calibration

Inspect: A framework for large language model evaluations

PyTorch native quantization for training and inference

DeepTeam is a framework to red team LLMs and AI agents.

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/