Top Open Source AI Organization Influencers in 2024Q3

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

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Efficient Triton Kernels for LLM Training

Multilingual Voice Understanding Model

Master Any Code: One-Click Comments and Language Conversion. 掌握任何屎山代码：一键注释和语言转换。💪

Zero shot pdf OCR with gpt-4o-mini

In-browser Postgres sandbox with AI assistance

Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Hackable open-source version of Anthropic's AI Artifacts chat

Llama3.1 learns to Listen

参考GraphRag使用 Semantic Kernel 来实现的dotnet版本

AUITestAgent is the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification.

LlamaVoice is a llama-based large voice generation model, providing inference and training ability.

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Chat with your data, modify it, visualize it, create and test machine learning models all in plain English. DataHorse makes data analysis and data science conversational using LLMs.

Finetune Llama-3-8b on the MathInstruct dataset

E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. It’s easy to install, with dedicated parsers and converters, supporting custom configs. E2M offers an all-in-one, flexible, and open-source solution.

开箱即用的基于企业私有知识库的LLM大语言模型的智能客服机器人问答系统，支持私有化部署，代码免费开源且可商用，由芝麻小客服官方推出。

LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1

[ECCV 2024] - Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation

🎉 The code repository for "Parrot: Multilingual Visual Instruction Tuning" in PyTorch.

Test Llama 3.1 tool calling

🛒 Adds AI assistance to Amazon shopping

ROS2 nodes for LLM, VLM, VLA

An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT

Function calling using Amazon Bedrock with Anthropic Claude 3 foundation model

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

A proxy sidecar to access Gemini models via OpenAI and Ollama APIs

exchange is a uniform python SDK for message generation with LLMs

Full stack tools for building voice agents

Examples for QinYan GLMs

Library for evaluating RAG using Nuclia's models

Oak National Academy's AI Auto Eval tools provide LLM as a judge evaluation on lesson plans and resources

Hosting Langfuse on Amazon ECS with Fargate using CDK Python

A demonstration of chatting with uploaded images using OpenAI vision models like gpt-4o.

Stable Diffusion WebUI Forge docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

Realign is a AI testing and simulation framework for multi-turn AI applications. It simulates user interactions, evaluates AI performance, and generates adversarial scenarios to test LLM vulnerabilities.

Yet another coding assistant powered by LLM.

[MICCAI'24] Incorporating Clinical Guidelines through Adapting Multi-modal Large Language Model for Prostate Cancer PI-RADS Scoring

Solving conversation problem for the deaf using STT, LLMs and TTS

🎉 A curated list of awesome things related to Claude Artifacts

This SDK generates datasets for training Video LLMs from youtube videos.

GraphFleet is an open-source knowledge for LLM apps

RAG with LLama Index

Unimpeded: Convert Poe.com to OpenAI Interface-Compatible Format! 🔑 畅通无阻: 将 Poe.com 转换为 OpenAI 接口兼容格式!

converts Vertex AI API to OpenAI API format.

Enable AI agents to communicate with humans in tool-based and asynchronous workflows. Guarantee human oversight of high-stakes function calls with approval workflows across slack, email and more. Bring your LLM and Framework of choice and start giving your AI agents safe access to the world. Agentic Workflows, human in the loop, function calling

Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), and text-to-speech (TTS) capabilities.

GuardAI leverages multiple AI models, including OpenAI, Gemini, and custom self-hosted AI servers, to scan code for security vulnerabilities.

Typesafe prompt construction for LLM inference with zod-parsed results

"Don't write any code, just tell what to do!"

Blocks for your AI applications, build delightful UX with effortless DX

Function-calling API for LLM from multiple providers

Official repository of "When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering"

A Rust library for using stable diffusion functions when the Wasi is being executed on WasmEdge.

一隻聰明的AI牛

조코딩 AI 해커톤 with Google / Tag Doctor Front Repository

Open-source, cost-effective alternative for teams using ChatGPT & Claude featuring multiple AI models, organized threads, team chat and more.

Scrape and Filter Publications using LLMs

Part of the LangChain.NET project. Has separate abstractions, does not contain dependencies on the main project and can be used independently

AI-Powered Code Review for Smart Contracts

.NET samples for LM-Kit.NET

Dockerfile for llamacpp

ACLReady, a retrieval-augmented language model application that can be used to empower authors to reflect on their work and assist authors with the ACL checklist.

The official integration for Apify and Haystack 2.0

A chatbot for the University of Massachusetts Lowell

A package for building RAG chatbot applications for educational contexts.

The Lancet “Picture Quiz Gallery” - VLM Image Challenge

The library management website is built to provide a platform for users to manage their books and resources. It allows users to easily borrow, return, and track library items. Library staff can quickly access information about resources and efficiently manage all operations.

A simple notebook for Stable Diffusion 3

Open source alternative of ChatGPT-4o, FREE!

Create a OpenAI chat app with Streamlit using GPT 4o model

조코딩 AI 해커톤 with Google / Tag Doctor Server Repository

에레메스

에레메스

Open-source AI chatbot for technical documentation websites

A simple, open-source Learning Management System.

:exclamation: This is a read-only mirror of the CRAN R package repository. gemini.R — Interface for 'Google Gemini' API. Homepage: https://github.com/jhk0530/gemini.R Report bugs for this package: https://github.com/jhk0530/gemini.R/issues

Exploring GPT-4o and Beyond published by Packt

Conversational Assistant with GPT-4o with Speech Function.

Conversational Assistant with GPT-4o with Speech Function (Soon to be deprecated).

Sample code for a simple web chat experience through Azure OpenAI, including Azure OpenAI On Your Data.