Open-source repositories gaining traction right now.
316 repositories

Star mlflow / mlflow The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.

[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

Dimensional is the agentic operating system for physical space. Vibecode humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).

A framework for efficient model inference with omni-modality models

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


LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Star exo-explore / exo Run frontier AI locally.

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

You like pytorch? You like micrograd? You love tinygrad! ❤️

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

Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.

Structured Outputs

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Star getzep / graphiti Build Real-Time Knowledge Graphs for AI Agents


A benchmark built to evaluate and improve agent capabilities for supporting legal work.

Star Cinnamon / kotaemon An open-source RAG-based tool for chatting with your documents.

Star Future-House / paper-qa High accuracy RAG for answering questions from scientific documents with citations

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer


Star NVIDIA-NeMo / NeMo 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

Star strands-agents / sdk-python A model-driven approach to building AI agents in just a few lines of code.

Star SemiAnalysisAI / InferenceX Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 vs H100 & soon™ TPUv6e/v7/Trainium2/3

Star NVIDIA-NeMo / Automodel Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Star open-webui / open-webui User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Star karpathy / nanoGPT The simplest, fastest repository for training/finetuning medium-sized GPTs.

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

Star google / langextract A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork


Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Star TEN-framework / ten-framework Open-source framework for conversational voice AI agents

"ClawWork: OpenClaw as Your AI Coworker - 💰 $10K earned in 7 Hours"

Star THUDM / slime slime is an LLM post-training framework for RL Scaling.

GLM-OCR: Accurate × Fast × Comprehensive

Star KellerJordan / modded-nanogpt NanoGPT (124M) in 2 minutes

Star OpenBMB / UltraRAG A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.

Advancing Open-source World Models

Star disler / claude-code-hooks-mastery Master Claude Code Hooks

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Visual Causal Flow


Code to load DreamZero model checkpoints and run evaluation on DROID-sim and Genie Sim 3.0

A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.


A Simple Implementation of Qwen3-TTS's ComfyUI

Causal video-action world model for generalist robot control

A Pragmatic VLA Foundation Model

Masked Depth Modeling for Spatial Perception


MOVA: Towards Scalable and Synchronized Video–Audio Generation

Local AI Agent running on Raspberry Pi

Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

Secure runtime for AI agents, and tools -- free and open-source from Celesto AI 🧡
Paste a github.com URL. Submissions are reviewed before they are tracked.