gpt4o 开源项目推荐（170 个）

EwingYangs /awesome-open-gpt

GPT 相关开源项目合集，精选

River-Zhang /ICEdit

[NeurIPS 2025]图像编辑值得一次LoRA！0.1%的训练数据，可进行出色的图像编辑！ID持久性超越GPT-4 o ~ MoE ckpt发布！仅4GB VRAM即可运行！

jishengpeng /WavTokenizer

[ICLR 2025] SOTA离散声学编解码模型，每秒40/75个令牌用于音频语言建模

Robitx /gp.nvim

Gp.nvim（GPT prompt）Neovim AI 插件：ChatGPT 会话、可指令式文本/代码操作、语音转文本 [OpenAI、Ollama、Anthropic 等]

ferrislucas /promptr

Promptr is a CLI tool that applies plain language instructions to the filesystem. Instructions can utilize a liquidjs based templating system. Use cases include refactoring, code generation, and experimentation.

GURPREETKAURJETHRA /END-TO-END-GENERATIVE-AI-PROJECTS

基于 LLM 模型的端到端生成式 AI 行业项目及部署_Awesome LLM Projects

ictnlp /LLaVA-Mini

LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.

a37836323 /-chatgpt4.0-api-key

🌥️ 云雾API | OpenAI官方中转服务 🌥️ https://yunwu.ai 🔥 官方价格0.5:1 🔥 0.5元=1$ Token 🔥 高性价比 稳定快速！ 🔥 | 全球直连 | 无需代理 | 企业级稳定 | gpt3.5 | gpt4 | gpt4o | gpt4o-mini | 207+模型支持

zjunlp /OmniThink

[EMNLP 2025] OmniThink：通过思考拓展机器写作中的知识边界

xiaoachen98 /Open-LLaVA-NeXT

An open-source implementation for training LLaVA-NeXT.

mbzuai-oryx /VideoGPT-plus

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

theyashwanthsai /Devyan

Building a Software Dev Team. Experimental Project to orchestrate a team of agents to solve programming tasks.

KingNish24 /OpenGPT-4o

OpenGPT 4o is a free alternative to OpenAI GPT 4o

sjinnovation /CollabAI

CollabAI is an open-source & self-hosted AI operation platform for small and medium-sized businesses. It’s a customizable & team-centric platform where you can have access to custom AI agents tailored to your business needs.

bjarneo /tAI

tAI is an AI terminal assistant CLI that helps you with Linux and macOS commands.

tryAGI /Tiktoken

High-performance .NET BPE tokenizer — up to 618 MiB/s, competitive with Rust. Zero-allocation counting, multilingual cache, o200k/cl100k/r50k/p50k encodings + HuggingFace tokenizer.json support.

ecornell /ai-tools-ahk

AI Tools - AutoHotkey - Enable global hotkeys to run custom OpenAI and Gemini prompts on text in any window.

GURPREETKAURJETHRA /Generative-AI-LLM-Projects

Gen AI Large Language Model Projects

reidbarber /webmarker

Mark web pages for use with vision-language models

DedInc /bingart

是一个非官方的 Bing Image & Video Creator 异步 API 封装。它允许你使用必应的图像创建工具以编程方式生成 AI 驱动的图像。