Top Open Source AI Dev Influencers in January 2025

Fully open reproduction of DeepSeek-R1

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

A GUI Agent application based on UI-TARS(Vision-Lanuage Model) that allows you to control your computer using natural language.

Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding

A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

A simple open-source chat app that uses Exa's API for web search and Deepseek R1 for reasoning

Bringing together outstanding artificial intelligence (AI) open source projects from around the world.

VS Code extension for LLM-assisted code/text completion

Deploy a Gemini multimodal chat website in 10 seconds, Severless! 只需准备一个Gemini API Key，10秒即可部署一个Gemini多模态对话的网站。

Make any LLM to think like OpenAI o1 and deepseek R1

Force DeepSeek r1 models to think for as long as you wish

Laravel wrapper for Deepseek PHP client, to seamless deepseek API integration with laravel applications.

GPT-4o-level, real-time spoken dialogue system.

Notate is a desktop chat application that takes AI conversations to the next level. It combines the simplicity of chat with advanced features like document analysis, vector search, and multi-model AI support - all while keeping your data private.

chatbot made with gradio using opensource deepseek-r1 running locally

💃 Dance with LLM in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.

Model Context Protocol server for DeepSeek's advanced language models

SynthLang is a hyper-efficient prompt language designed to optimize interactions with Large Language Models (LLMs) like GPT-4o by leveraging logographical scripts and symbolic constructs.

Simple extension on vLLM to help you speed up reasoning model without training.

Deepseek V3 and R1 private API, deep thinking, search, full requests. pow challenge reversed. deepseek api.

Go (Golang) client for Deepseek API. Deepseek Go supports DeepSeek-V3, DeepSeek-R1 and more

A UI client for Ollama written in Compose Multiplatform focused on running Deepseek r1 locally

Dive is an open-source AI Agent desktop application that seamlessly integrates any Tools Call-supported LLM with frontend MCP Server—part of the Open Agent Platform initiative.

Deepseek-R1 Tools and guide

Open replication of DeepSeek R1 for text-to-graph extraction.

Community maintained hardware plugin for vLLM on Ascend

Chat with PDF using LangChain, Streamlit, Ollama (for LLM inference) and PDFPlumber. Overall which is an example of a Retrieval-Augmented Generation (RAG) system with Deepseek r1 model.

Demonstrates how to build a streaming enterprise agent using Azure AI Agent Service. This sample integrates local HR and company policy documents, Bing for external context, and GPT-4o (though the service is model-agnostic) to deliver real-time Q&A and automated workflows.

An AI Writing Assistant for Emacs

Make your LLM agent and chat with it simple and fast!

Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU inference.

A simplified implementation for experimenting with Reinforcement Learning (RL) on GSM8K, inspired by RLVR and Deepseek R1. This repository provides a starting point for exploring RL-based reasoning.

Build a powerful AI-driven retrieval-augmented generation (RAG) system using Ollama and DeepSeek R1.

Graph Foundation Model for Retrieval Augmented Generation

RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.

Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.

AI agent to search Google Flights data

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine 🤔

A curated list of projects related to deepseek

Meet WebHive, the AI-powered browser that takes care of tasks for you. No more endless clicks, tell it what you need, and it gets it done.

DeepSeek-R1本地化WebUI运行

ScalarLM - a unified training and inference stack

Run DeepSeek R1 models locally using Docker. Interact with the model through a browser-based UI or CLI using Ollama.

AIN - The First Arabic Inclusive Large Multimodal Model. It is a versatile bilingual LMM excelling in visual and contextual understanding across diverse domains.

[ICLR 2025] NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals

A collection of awesome web2 and web3 AI agents and workflows using OpenAI compatible LLMs.

AI-powered reasoning engine powered by DeepSeek R1 reasoning model to refine queries, synthesize data, and provide insightful research responses.

Deepseek R1 Agent powered by LMStudio and Smolagents

A powerful tool for cursor through DeepSeek R1.(DeepSeek R1,o1,etc.)

how to run DeepSeek-R1-Distill-Qwen-1.5B GGUF locally on your PC

高质量的思科模拟器汉化 CiscoPacketTracerChinese 通过使用智谱清言的 glm-4-plus 大模型 进行翻译，并结合后期人工矫正，达到了前所未有的汉化质量。

First-ever Discord Bot with Deepseek R1 (Runs locally or with API)

PageRank for LLMs

Linq's Function Calling Agent utilizing DeepSeek-R1

Running Deepseek R1 Local on Ollama

a MCP server which integrates reasoning capabilities of DeepSeek R1 model into claude desktop app.

A framework making it effortless to convert any llm model into a reasoning agent like o1 or DeepSeek's r1

An AI-powered tool for summarizing YouTube videos by generating scene descriptions, translating them, and creating subtitled videos with text-to-speech narration

Coffee Chat Voice Assistant is a voice-driven ordering system powered by Azure OpenAI GPT-4o Realtime API, simulating the experience of ordering coffee with a café barista. It supports natural conversations, live order updates, and real-time transcription, showcasing the power of AI for seamless customer interactions.

An implementation of the DISP-LLM method from the NeurIPS 2024 paper: Dimension-Independent Structural Pruning for Large Language Models.

This repository provides an AI-powered trading bot leveraging AlloraNetwork for automatic trading on HyperLiquid decentralized exchange. The bot integrates predictive insights and customizable strategies for seamless trading. 🌟

Models: Deepseek R1 models, Llama3.2, Qwen2.5. Integrations: Ollama, Gradio. Supports Local LLM. Test and deploy the latest LLM models in the fastest and most efficient way

Interactive environment to explore DeepSeek-R1 on Google Colab, featuring Gradio UI and LangChain pipelines, with Ollama as the model runtime.

LM Agent for Operating Systems Course Assistance

A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning R1 mentorship capabilities, including code review, design critique, writing feedback, and idea brainstorming through the Deepseek API.

Official PyTorch implementation for "MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens"

一个基于WebSocket和LLM的实时语音对话系统，集成了语音识别(ASR)、大语言模型(LLM)和语音合成(TTS)功能。

DeepSeek R1 distilled into smaller OSS models

Deploy Amazon DeepSeek R1 Models on Amazon Bedrock

强大的浏览器插件，支持deepseek r1直接以侧边栏的形式和页面进行交互。

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Hana is an AI agent built with the Zen package.

An LLM-powered chatbot for fediverse. A tech demo for BotKit.

Enable your ollama model to participate in online chats.

AI-powered computer control for automated testing. FactifAI uses vision models (Claude, GPT-4o, Gemini) to interact with applications naturally - clicking, typing, and verifying results just like a human would.

This project is a web-based PDF question-answering chatbot powered by Deepseek v3 and R1's Language Learning Models (LLMs). Users can upload PDFs, ask questions related to the uploaded documents, and receive accurate responses. Use the link below to try it out!

This is my playground using google colab to serve some deepseek model so it can be hit by external party (right now i'm using curl and postman).

Run DeepSeek R1 model on an Ubuntu single board computer without user registration.

Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?

A curated collection of research, tools, and best practices for environmentally sustainable AI development and deployment.

This is a simple example of how to serve a DeepSeek model with Azure ML.

Your self-hosted AI assistant. Interactive Shell, Files and Folders analysis. Powered by Ollama.

The official code of "PixelWorld: Towards Perceiving Everything as Pixels"

Securade.ai Sentinel - A monitoring and surveillance application that enables visual Q&A and video captioning for existing CCTV cameras.

Futurestic-Ai is an innovative artificial intelligence platform designed to revolutionize the way businesses operate by providing advanced predictive analytics and automation capabilities. It offers cutting-edge solutions for optimizing processes, identifying trends, and making intelligent decisions based on real-time data analysis.

ComfyUI-DeepSeek-Toolkit is a node developed within the ComfyUI framework, designed to bring powerful LLMs like DeepSeek and Qwen into practical ComfyUI development. The goal is to leverage the capabilities of these advanced LLMs to create a series of useful nodes for ComfyUI.

My DeepSeek-R1 local machine test.

Ops files for https//github.com/meta-llama/llama-stack