Top Open Source AI Dev Influencers in October 2024

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Janus-Series: Unified Multimodal Understanding and Generation Models

Suna - Open Source Generalist AI Agent

verl: Volcano Engine Reinforcement Learning for LLMs

📃 A better UX for chat, writing content, and coding with LLMs.

GLM-4-Voice | 端到端中英语音对话模型

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

An Open Source implementation of Notebook LM with more flexibility and features

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

《Build a Large Language Model (From Scratch)》是一本深入探讨大语言模型原理与实现的电子书，适合希望深入了解 GPT 等大模型架构、训练过程及应用开发的学习者。为了让更多中文读者能够接触到这本极具价值的教材，我决定将其翻译成中文，并通过 GitHub 进行开源共享。

The world's smartest system-wide grammar assistant; a better version of the Apple Intelligence Writing Tools. Works on Windows, Linux, & macOS, with the free Gemini API, local LLMs, & more.

Vim plugin for LLM-assisted code/text completion

Use ChatGpt 4o forFree - No API Key Need. also ChatGpt 3 and ChatGpt 3.5 Experience the power of ChatGPT with a user-friendly interface, enhanced jailbreaks, and completely free.

实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

Model swapping for llama.cpp (or any local OpenAPI compatible server)

Azure OpenAI code resources for using gpt-4o-realtime capabilities.

Large Reasoning Models

Rime输入法语法模型全流程构建教程，全局带声调词库，最全声调标注工具链：LMDG - Language, Model, Dictionary, Grammar。Q群：11033572

Parsing-free RAG supported by VLMs

AI assisted programming in Emacs with Aider

Apple MLX engine for LM Studio

Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs

Python API client for AI providers that intends to replace LangChain and LangGraph for most common use cases.

Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!

VSCode for the new age of AI.

Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents

PDF 生成中文播客

Chat UI components for LLM apps

Generate large synthetic data using an LLM

JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

Codai is an AI code assistant that helps developers through a session-based CLI, providing intelligent code suggestions, refactoring, and code reviews based on the full context of the project.

🤠 Agent-as-a-Judge and DevAI dataset

Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI

A simple Python program to implement the search-extract-summarize flow.

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR25]

📋 NotebookMLX - An Open Source version of NotebookLM (Ported NotebookLlama)

Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

Engy is an AI-powered development tool that generates fully functional web applications from natural language, streamlining the process from idea to working prototype.

AI toolkit for making Shorts/Tiktoks

An LLM-powered programming-by-example programming language.

[ICLR2025] MagicPIG: LSH Sampling for Efficient LLM Generation

Open source AI analyst powered by E2B. Analyze your CSV files with Llama 3.1 and create interactive charts.

MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for LLMs.

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

Ollama client written in Python

The official implementation of the paper "AgentSquare: Automatic LLM Agent Search in Modular Design Space""

Write and execute jq programs with the help of LLM

Hands-on tutorials on fine-tuning various LLMs using different fine-tuning techniques

For LLMs to better code with Jina API

An easy-to-understand framework for LLM samplers that rewind and revise generated tokens

A GitHub Action that automatically reviews pull requests using Google's Gemini AI.

Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research

An image viewer and AI-assisted editing/captioning/masking tool that helps with curating datasets for generative AI models, finetunes and LoRA.

LearnGo, a ios versatile learning tool with RAG and Prompting under LLM like GPT-4o-mini, enabling subject Q&A, smart note generation from uploaded materials, offline photo(or AR) object recognition with translations, and multilingual voice input (Cantonese, English, Mandarin). It also features customizable themes for a personalized experience

A light llama-like llm inference framework based on the triton kernel.

A command-line personal assistant that integrates with Google Calendar, Gmail, and Tasks to help manage your digital life.

Execute agentic workflows defined in simple YAML files

✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

[NeurIPS 2024] SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation

A replication of Andy Ayrey's "Backrooms" (https://dreams-of-an-electric-mind.webflow.io/), but runnable with Opus 3, Sonnet 3.5, GPT 4o, and o1-preview

The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".

Official Implementation of "Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models".

A Ruby gem for seamlessly and uniformly interacting with large language and vision model (LLM) API's served by numerous services, including those of OpenAI, Anthropic, Google and others.

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Lightweight Multi Agent AI Orchestrator Framework with AGI Capabilities.

[arXiv 2024] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

💬 AI Chat Bot demo app showcasing the integration of Gemini SDK with Firebase Realtime Database for real-time chat functionality.

A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability

[CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding

LLM assistants for R

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models

Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".

This repository is for the paper entitled: From News to Forecast: Integrating Event Analysis in LLM-based Time Series Forecasting with Reflection (NeurIPS 2024)

Chat with PDF using Llama 3.3

An introduction to LLM Sampling

LogLLM: Log-based Anomaly Detection Using Large Language Models (system log anomaly detection)

[ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"

NotebookLlama powered by Groq - Create podcasts on any topic lightning fast

Web Agent is an automation tool driven by AI. Designed for seamless navigation and task execution on the web, it intelligently interacts with dynamic web elements, performs searches, downloads files, and adapts to page changes.

Sparse Autoencoders for Stable Diffusion XL models.

最新ChatGPT Plus合租攻略：国内最靠谱的ChatGPT Plus拼车平台推荐(每月仅27元)！可使用GPT-4o生图功能和GPT-4.1系列模型，还支持满血版DeepSeek-R1、马斯克的Grok-3和谷歌Gemini-2.5 Pro！如果你无法解决科学上网的问题，或觉得每月20美元的会员费用过高，可以考虑ChatGPT Plus共享合租帐号。这种方式不仅能够降低使用成本，还免去了科学上网的复杂操作。

Building a GPT-like LLM from scratch with PyTorch.

Sparse Inferencing for transformer based LLMs

[IROS 2025] Human Demo Videos to Robot Action Plans

Frontend Engine Extension for Stable Diffusion Web UI and Stable Diffusion Web UI Forge.

PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture incorporates a novel Differential Attention mechanism, Multi-Head structure, RMSNorm, and SwiGLU.

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Graphy v1: A Realtime GraphRAG App using Langchain, Neo4j, GPT-4o, and Streamlit.

Automatically generate engaging AI podcasts from nothing but an episode title.

Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"

This is a tool that can automatically translate the chat log into a note using LLM API

Official implementation of "Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy."

Official implementation of "GPT or BERT: why not both?"