Awesome Opensource Ai

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

DeepSeek Coder: Let the Code Write Itself

Graph Neural Network Library for PyTorch

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

The open-source alternative to Claude Cowork (powered by opencode)

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

Universal LLM Deployment Engine with ML Compilation

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Temporal service

"RAG-Anything: All-in-One RAG Framework"

Open-source vector similarity search for Postgres

No description.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

A high-performance observability data pipeline.

Hindsight: Agent Memory That Learns

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

A guidance language for controlling large language models.

🤗 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

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

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

Development repository for the Triton language and compiler

Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

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 TTS model capable of generating ultra-realistic dialogue in one pass.

Toolkit for linearizing PDFs for LLM datasets/training

AI Agent Framework, the Pydantic way

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.

The most RAM efficient harness

Train transformer language models with reinforcement learning.

State-of-the-Art Embeddings, Retrieval, and Reranking