Repository History
Explore all analyzed open source repositories
Qwen3: Alibaba Cloud's Advanced Large Language Model Series
Qwen3 is a powerful series of large language models developed by the Qwen team at Alibaba Cloud. It offers advanced capabilities in reasoning, multilingual support, and long-context understanding, available in various sizes and modes for diverse applications. This repository provides comprehensive resources for running, deploying, and building with Qwen3 models.
AI-Scientist-v2: Automated Scientific Discovery via Agentic Tree Search
AI-Scientist-v2 is an advanced agentic system designed for automated scientific discovery, capable of generating hypotheses, running experiments, analyzing data, and writing scientific manuscripts. This system has successfully produced the first workshop paper written entirely by AI and accepted through peer review, marking a significant step towards fully autonomous research.
WeClone: Create Your AI Digital Twin from Chat History with LLMs
WeClone is an innovative open-source project that provides a comprehensive solution for creating your personal AI digital twin. It allows users to fine-tune Large Language Models (LLMs) using their chat history, capturing unique communication styles. The resulting AI can then be integrated with various chatbots, bringing your digital self to life.
oobabooga/text-generation-webui: The Premier Local LLM Interface
oobabooga/text-generation-webui is a powerful and versatile web UI for running large language models (LLMs) locally. It offers a 100% offline and private environment for text generation, vision, tool-calling, and even training, all accessible through an intuitive interface and API.
rag-from-scratch: Building Retrieval Augmented Generation Systems
This repository by LangChain AI offers a comprehensive guide to understanding and implementing Retrieval Augmented Generation (RAG) from scratch. It includes a series of Jupyter notebooks and an accompanying video playlist, making complex RAG concepts accessible for practical application. The resource highlights RAG's advantages over fine-tuning for factual recall in Large Language Models (LLMs).
AgentStack: The Fastest Way to Build Robust AI Agents
AgentStack is a powerful command-line tool designed to simplify the development of AI agents. It provides a scaffold for agent projects, offering CLI utilities for code generation and managing various LLMs, frameworks, and tools. This project aims to make building robust AI agents accessible and efficient for developers.
Chatterbox: State-of-the-Art Open-Source Text-to-Speech by Resemble AI
Chatterbox is a powerful family of open-source text-to-speech (TTS) models developed by Resemble AI, designed for high-quality speech generation. It features Chatterbox-Turbo, an efficient model with paralinguistic tags for added realism, alongside multilingual and general-purpose TTS options. These models provide robust solutions for voice agents, narration, and creative workflows, incorporating responsible AI features like built-in watermarking.
Strands Agents SDK-Python: Model-Driven AI Agent Development
Strands Agents SDK-Python offers a powerful, model-driven approach to building AI agents with minimal code. It supports a wide range of model providers and advanced capabilities like multi-agent systems and bidirectional streaming, scaling from local development to production. This Python SDK simplifies the creation of intelligent agents for various applications.
Kimi-k1.5: Scaling Reinforcement Learning with LLMs and Multimodality
Kimi-k1.5 introduces an o1-level multi-modal model that significantly advances reinforcement learning with Large Language Models. It demonstrates state-of-the-art performance in short-CoT tasks, outperforming leading models like GPT-4o and Claude Sonnet 3.5, and matches o1 performance in long-CoT scenarios across various modalities. This project highlights key innovations in long context scaling and improved policy optimization.
judges: A Python Library for LLM-as-a-Judge Evaluators
The `judges` library from Databricks provides a concise and powerful way to use and create LLM-as-a-Judge evaluators. It offers a curated set of pre-built judges for various use cases, backed by research, and supports both off-the-shelf usage and custom judge creation. This tool helps developers effectively evaluate the performance and quality of their Large Language Models.
Spark-TTS: Efficient LLM-Based Text-to-Speech with Zero-Shot Voice Cloning
Spark-TTS is an advanced text-to-speech system that leverages large language models (LLM) for highly accurate and natural-sounding voice synthesis. Built on Qwen2.5, it offers streamlined efficiency, high-quality zero-shot voice cloning, bilingual support for Chinese and English, and controllable speech generation, making it versatile for both research and production.
TRELLIS: Structured 3D Latents for Scalable and Versatile 3D Generation
TRELLIS is the official repository for a CVPR'25 Spotlight paper on "Structured 3D Latents for Scalable and Versatile 3D Generation." This Microsoft project introduces a powerful model for generating high-quality 3D assets from text or image prompts. It supports diverse output formats like Radiance Fields, 3D Gaussians, and meshes, offering flexible editing capabilities.