Awesome Opensource Ai

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

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

open-source agentic AI data assistant for the next generation of AI + Data products.

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Mamba SSM architecture

High-performance In-browser LLM Inference Engine

Hindsight: Agent Memory That Learns

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Datasets, Transforms and Models specific to Computer Vision

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Network Analysis in Python

Ongoing research training transformer models at scale

Workflow Engine for Kubernetes

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

An orchestration platform for the development, production, and observation of data assets.

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

FinRL®: Financial Reinforcement Learning. 🔥

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

Tensor library for machine learning

Simple, unified interface to multiple Generative AI providers

Unified framework for building enterprise RAG pipelines with small, specialized models

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

SciPy library main repository

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Structured Outputs

The Open Context Layer for Data and AI , OpenMetadata is the open platform for building trusted data context and business semantics for humans, AI assistants, and agents.

Multi-Joint dynamics with Contact. A general purpose physics simulator.

Open-source simulator for autonomous driving research.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

An open source implementation of CLIP.

Open3D: A Modern Library for 3D Data Processing

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

structured outputs for llms

Open Source framework for voice and multimodal conversational AI

A framework for few-shot evaluation of language models.

Minimal reproduction of DeepSeek R1-Zero

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

No description.

The Context Platform for your Data and AI Stack