My own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.

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

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

Solve Visual Understanding with Reinforced VLMs

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。

推荐使用DeepSeekV3。可以接入微信、QQBot。基于LLM的更逼真的情感陪伴程序。内置了 Atri-My dear moments 的 prompt。Built-in prompt for Atri My dear moments.Support WeChat& QQBot. More realistic emotional companionship program based LLM, meet the characters in your dream.

(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

基于DeepseekR1/Gemini2/GoogleVison2/GoogleSearch API实现的深度思考联网多模态大模型。

Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

Local LLM Powered Recursive Search & Smart Knowledge Explorer

[arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices

Reliable Automation Agents at Scale

🔬 Visualize attention layers from Stable Diffusion

SOTA RL fine-tuning solution for advanced math reasoning of LLM

fine-tune deepseek r1

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.

Super-easy AI Agent Library specialized for LLM function calling

Using the moondream VLM with optical flow for promptable object tracking

Enhanced BurpGPT 是一个强大的 Burp Suite 插件。通过分析指定的 HTTP 请求和响应，帮助安全测试人员更快速地发现潜在的安全漏洞。

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

GRPO for VLMs

micro llm pt/sft/grpo from scratch

Chitrarth: Bridging Vision and Language for a Billion People

用于astrbot，使用Stable Diffusion WebUI的API进行图片生成的插件。

AI ChatBox是一个基于MFC框架开发的本地AI聊天程序，集成了大型语言模型，支持多轮对话，对话记录保存等功能。用户可以选择不同的本地模型，例如qwen、llama、deepseek等，进行对话。AI ChatBox完全离线运行，保护用户隐私

AI智能对话系统，整合了国际化、在线代码生成、AI对话、AI联网功能、发送图片、RGA对话、AI工具等。AI Intelligent Conversation System, integrates common functions of the backend management system, internationalization, online code generation, AI conversation, AI development tools, RGA chat...

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

call center、contact center、呼叫中心、联络中心中：LLM,Chatbot,GPT,DeepSeek,Gemini,Claude,LLaMA,Qwen,豆包等等，这些在线客服、大模型聊天机器人等网页AI坐席，AI处理不了之后，转人工坐席。获取在线客服状态与电话坐席状态，可通过策略，进行统一排队。

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

CLI tool that helps you write clear, concise, and AI-generated commit messages using OpenRouter's LLM models.

Open-source clone of OpenAI's Deep Research. Works with any transformer, gpt4free, & runs in browser. No Firecrawl needed.

Chrome extension for translating from Persian to English and from English to Persian using Google Gemini API.

一个借助 Gemini 2.0 多模态模型评估你音乐的编曲、人声、歌词等各维度的 Web APP

智谱AI 2024年金融行业大模型挑战赛 48分方案

The objective of this project is to demonstrate how to fine-tune deepseek-r1-distill-llama-8b.

Do literature review Fast, Simple and Reliable

READ THE README

【2月最新更新】ChatGPT 中文版：国内直连指南（支持GPT-4、GPT-4o、GPT-o1，无需翻墙）

gemini protocol browser

Interactive Seminars with Real-time Feedback and Gemini based Q&A

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

lm-studio-ollama-bridge is a standalone Go-based utility that synchronizes your local Ollama models with external applications such as LM Studio. Inspired by the original matts-shell-scripts/syncmodels project

FastLLM - Rust based LLM Inference API

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

智谱 glm realtime api python sdk, 包括一个 low level 的 websocket client 封装以及各个场景的调用样例

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

An open-source alternative to OpenAI and Gemini's deep research.

一个可以方便白嫖 Google gemini pro 2.0 的移动客户端

This repository highlights my learning journey in building Retrieval-Augmented Generation (RAG) pipelines using DeepSeek on Lightning AI, covering document ingestion, retrieval, and integration with generative AI. It showcases fine-tuning, evaluation, and optimization for accurate open-domain QA and knowledge management.

Explore DeepSeek R1🚀: reproduction guides, papers, insightful tweets&blogs to explore and learn. 🌟

A proof of concept model based on Llama 3.1-8B, featuring reasoning capabilities in Bulgarian.

A Python app that generates images from text prompts using Stable Diffusion.

A Flexible Multi-Model Orchestration API with OpenAI Compatibility

Help developers optimize AI application performance through comprehensive speed testing and analysis

RSS reader which fetch articles automatically & summarize using latest LLM

Embedded ChatGPT

Fine-tuning Qwen2.5-VL for vision-language tasks | Optimized for Vision understanding | LoRA & PEFT support.

Modules for Sora.

Discord App for Interacting with local Ollama Models. Multiple Agents Supported!

surf the small web - a gemini, spartan and nex browser

Create a Gemini Api Key for Resume ATS

An AI-native database designed for LLM applications, offering lightning-fast hybrid search across dense vectors, sparse vectors, multi-vector tensors, and full-text data.

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.

My personal LM & CV emailer tool (WIP)

LLaMA-Factory数据多模态数据标签可视化，Multimodal annotation viewer/editor, specialised for LLaMA-Factory.

PuPu is a lightweight tool that makes it easy to run AI models on your own device. Designed for smooth performance and ease of use, PuPu is perfect for anyone who wants quick access to AI without technical complexity.

A RAG (Retrieval-Augmented Generation) application which combines retrieval-based and generative approaches to improve the accuracy and relevance of AI-generated responses.

A batch captioning tool for SmolVLM-500M-Instruct

A high-performance Vision-Language Model (VLM) pipeline that extracts structured information from PDFs using Qwen2-VL, PyTorch, and Databricks GPU acceleration. Converts PDFs to images, processes them with deep learning, and outputs structured JSON data for analysis. 🚀

Revised version of SoraBot

My personal repository - CV, interests etc.

Stable diffusion model using .ckpt model file of v-1-4 original model with ComfyUI

Generate stunning AI images using Stable Diffusion with an intuitive ComfyUI interface. 🚀 ✅ Easy setup with ready-to-run scripts✅ ComfyUI Integration for seamless creativity✅ Automated Image Generation with customizable settings✅ Preloaded Sample Images to explore AI-generated art Unleash AI-powered creativity effortlessly! 🎨✨

This project explores the complete workflow of implementing Stable Diffusion v1-5-pruned-emaonly-fp16 using ComfyUI, from downloading the model to generating detailed AI-generated images.

image generation using stable diffusion and comfy ui Project Description: This repository showcases image generation experiments using Stable Diffusion, a powerful text-to-image AI model, and ComfyUI, a user-friendly graphical interface for controlling and customizing the generation process.

AI-driven image production has drawn a lot of interest lately since it makes it possible to create incredibly intricate and personalized images in response to text inputs. Through the use of deep learning models, this project investigates "Image Generation using Stable Diffusion & ComfyUI," producing high-quality images from textual descriptions.

This project uses Stable Diffusion with ComfyUI to generate images from text. It enables customizable, high-quality visuals for art, design, and content creation, making AI-driven creativity more accessible.

Image Generation Stable Diffusion & ComfyUI This repository demonstrates a project leveraging Stable Diffusion, a powerful text-to-image generation model, integrated with ComfyUI for enhanced usability and workflow customization. The project showcases the creative potential of generative AI by transforming textual prompts visually stunning images.

Stable diffusion model using .ckpt model file of v-1-4 original model with ComfyUI

GEN_AI project Video Generation by using the stable Diffusion

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

A simple web application that converts text prompts into AI-generated images using Stable Diffusion. Built with Flask and a lightweight frontend.

ComfyUI-powered Stable Diffusion image generation with a flexible and modular workflow.