Awesome Opensource Ai

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

the LLM vulnerability scanner

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Build autonomous AI agents in Python.

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

An open source python library for automated feature engineering

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

A vector search SQLite extension that runs anywhere!

Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.

Utilities intended for use with Llama models.

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

⚙️🦀 Build modular and scalable LLM Applications in Rust

Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.

Unified framework for robot learning built on NVIDIA Isaac Sim

Flax is a neural network library for JAX that is designed for flexibility.

Fast, flexible LLM inference

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

A repository of models, textual inversions, and more

Tools for merging pretrained large language models.

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

A Datacenter Scale Distributed Inference Serving Framework

The Open Source Feature Store for AI/ML

FinRobot: An Open-Source AI Agent Platform for Financial Analysis using LLMs 🚀 🚀 🚀

Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.

An app that brings language models directly to your phone.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

Adding guardrails to large language models.

SkyReels-V2: Infinite-length Film Generative model

lightweight, standalone C++ inference engine for Google's Gemma models.

Fit interpretable models. Explain blackbox machine learning.

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

No description.

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

✨ AI Coding, Vim Style

Deploy serverless AI workflows at scale. Firebase for AI agents

the portable Python dataframe library

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Modeling, training, eval, and inference code for OLMo

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Efficient Triton Kernels for LLM Training

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

TensorFlow documentation

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.