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.

Solve Visual Understanding with Reinforced VLMs

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

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.

Reliable Automation Agents at Scale

AI Pair Programming in Emacs

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

🔬 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

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

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.

READ THE README

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

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

【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）