Awesome Opensource Ai

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Open standard for machine learning interoperability

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Minimalist ML framework for Rust

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Development repository for the Triton language and compiler

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

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

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.

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.

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

Agent Skills for Google products and technologies

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

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

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

🐫 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)

Ongoing research training transformer models at scale

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

Network Analysis in Python

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

Workflow Engine for Kubernetes

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​.

Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.

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.

FinRL®: Financial Reinforcement Learning. 🔥

Simple, unified interface to multiple Generative AI providers

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

Structured Outputs

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

Tensor library for machine learning

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

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

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.

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.

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.

Open-source simulator for autonomous driving research.

An open source implementation of CLIP.