Awesome Opensource Ai

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

an ambient intelligence library

A scikit-learn compatible neural network library that wraps PyTorch

Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.

Open-source scientific and technical publishing system built on Pandoc.

A system for quickly generating training data with weak supervision

An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

A model-driven approach to building AI agents in just a few lines of code.

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

A treasure chest for visual classification and recognition powered by PaddlePaddle

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Democratizing Reinforcement Learning for LLMs

Chronos: Pretrained Models for Time Series Forecasting

Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.

PyTorch native post-training library

🐢 Open-Source Evaluation & Testing library for LLM Agents

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

A PyTorch native platform for training generative AI models

Gemma open-weight LLM library, from Google DeepMind

Model interpretability and understanding for PyTorch

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org

Robust recipes to align language models with human and AI preferences

CUDA accelerated rasterization of gaussian splatting

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

lakeFS - Data version control for your data lake | Git for data

Repository for skills to assist AI coding agents with .NET and C#

Supercharge Your Model Training

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

Header-only C++/python library for fast approximate nearest neighbors

Astronomy and astrophysics core library

A complete guide to start and improve in machine learning (ML), artificial intelligence (AI) in 2026 without ANY background in the field and stay up-to-date with the latest news and state-of-the-art techniques!

Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0

Simple and Distributed Machine Learning Python Library porting ML algorithms for Spark

Probabilistic time series modeling in Python

cuML - RAPIDS Machine Learning Library

Visualizer for pandas data structures

A Next-Generation Training Engine Built for Ultra-Large MoE Models

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Free, ultrafast Copilot alternative for Vim and Neovim