Awesome Opensource Ai

Reliable Multi-Agent Orchestration Framework

A fast multimodal LLM for real-time voice

A light-weight, flexible, and expressive statistical data testing library

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

Optimizing inference proxy for LLMs

AdalFlow: The library to build & auto-optimize LLM applications.

Machine Learning Pipelines for Kubeflow

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Official repository for the Boltz biomolecular interaction models

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

A system for agentic LLM-powered data processing and ETL

Harness LLMs with Multi-Agent Programming

OpenAgents - The collaboration OS for AI agents

Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.

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

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Simple, safe way to store and distribute tensors

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.

A flexible, high-performance 3D simulator for Embodied AI research.

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

Open-source multimodal retrieval engine (Morphik Core)

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.

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.

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

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

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

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

llama.cpp fork with additional SOTA quants and improved performance

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

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.

Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.

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