Fully open reproduction of DeepSeek-R1

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

Solve Visual Understanding with Reinforced VLMs

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

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

Witness the aha moment of VLM with less than $3.

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

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

An AI chat bot for small and medium-sized teams, supporting models such as Deepseek, Open AI, Claude, and Gemini. 专为中小团队设计的 AI 聊天应用，支持 Deepseek、Open AI、Claude、Gemini 等模型。

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

VS Code extension for LLM-assisted code/text completion

deepseek java sdk

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

Explore the Multimodal “Aha Moment” on 2B Model

⚡️ supercharged community-maintained PHP API client that allows you to interact with deepseek API

Flame is an open-source multimodal AI system designed to translate UI design mockups into high-quality React code. It leverages vision-language modeling, automated data synthesis, and structured training workflows to bridge the gap between design and front-end development.

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

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

Reliable Automation Agents at Scale

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.

Applying the ideas of Deepseek R1 to computer use

A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.

Autonomous software development agent apps using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more.

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

TypeScript Agentic AI Library specialized for LLM Function Calling enhanced by compiler skills.

Doge Family of Small Language Model

LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM

🧠🔗 Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

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.

Community maintained hardware plugin for vLLM on Ascend

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

探索 AI 的未來！聯發創新基地（MediaTek Research）首次開源的手機應用程式，讓你直接體驗我們最新研發的 AI 模型。透過手機，我們將 AI 科技帶入每個人的生活，完全離線運作，隱私更有保障。這是一個開源專案，我們熱烈歡迎開發者和愛好者一同參與，為 AI 技術發展貢獻力量。立即加入我們，一起打造更優質的 AI 體驗！

Prompts for deepseek， deepseek R1

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.

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

MoD Control Tile Upscaler for SDXL Pipeline

Demonstrate how to use DeepSeek-R1 models GitHub Models, Azure or Ollama

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

Linq's Function Calling Agent utilizing DeepSeek-R1

A user-friendly Command-line/SDK tool that makes it quickly and easier to deploy open-source LLMs on AWS

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

A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Convert LLaMA3.1-8B to DeepSeek R1 MLA & MoE (raw)

Reproduction of the complete process of DeepSeek-R1 on small-scale models, including Pre-training, SFT, and RL.

[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.

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.

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

A benchmarking tool for comparing different LLM API providers' DeepSeek model deployments.

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.

深海GLM大模型竞赛

智谱 glm realtime api python/golang sdk, 包括 low level 的 websocket client 封装以及各个场景的调用样例

Chitrarth: Bridging Vision and Language for a Billion People

an open-source, community-curated directory of contexts for use with LLMs

TypeScript SDK to call 100+ LLM Providers in OpenAI format.

A full-stack AI-powered microblogging application leveraging Azure Static Web Apps, Azure Functions, and Remix SSR with Azure OpenAI GPT-4o.

Chat with a Codebase using DeepSeek R1, Claude, GPT, Gemini

minRAG is a RAG system that starts from scratch, pursuing the ultimate simplicity and power. It consists of no more than 10,000 lines of code, requires no installation, and can be launched with a double-click

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

A distilled DeepSeek-R1 variant built on Qwen2.5-32B, fine-tuned with curated data for enhanced performance and efficiency. <metadata> gpu: A100 | collections: ["vLLM"] </metadata>

Official Node.js SDK for VLM Run

litemind is a Python library designed to empower developers to build sophisticated conversational agents and tools. It provides a flexible and elegant API for interacting with Large Language Models (LLMs) from various providers, along with a powerful agentic AI framework that supports multimodal inputs and outputs.

DeepSeek R1 Web App using Azure AI Foundry

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

Bag of Tricks for Inference-time Computation of LLM Reasoning

Flock 🐤🐧🐓🦆 # A declarative AI Agent Framework # JOIN THE FLOCK

They're training LLMs on your data. Let's give them exactly what we want them to learn

Note taking application, LLM enhanced.

See How Big Exactly A 128k Token Text Is

Decentralized LLMs fine-tuning and inference with offloading

EgoNormia | Benchmarking Physical Social Norm Understanding in VLMs

Telegram Chat-Bot with DeepSeek-R1 model

AM1 - Your own web application to do DeepResearch using any Multi-Agent Framework and underlying LLM to run on production servers or your laptop.

Serverless DeepSeek R1 Inference with FastAPI and Lambda SnapStart

LM Studio App and Developer Docs

Papers & resources linked to Transformer-based research mainly for transportation🚆🚗🛩️⛵️🛣️🚦.

Open Source Video Understanding API and Large Vision Model Observability Platform.

SO-ARM100 is a low-cost robotics project exploring training methods like Imitation Learning, Reinforcement Learning, VLMs, and Diffusion Policies. It aims to enhance autonomous control and decision-making by integrating advanced AI techniques into an affordable robotic system.

Llama Library Is library for inference any model ai LLAMA / LLM On Edge without api or internet quota, but need resources depends model you want run

WIP Stable Diffusion Library Stable Diffusion Is Library for generated text to Image

Outetts Is Library for generate neural Text To Speech on Edge Device Without api key or internet quota

Let your emotions guide the music. This research-oriented application focusses on zero-shot music recommendations using LLMs and VLMs based on multimodal diary management.

Repository to use for testing out Ollama Stack solutions

Code and data for LM Agents for Coordinating Multi-User Information Gathering