GPT-V-on-Web
Web Agent
An open source project that uses GPT-4 Vision to create an autonomous web agent with interactive capabilities.
👀🧠 GPT-4 Vision x 💪⌨️ Vimium = Autonomous Web Agent
163 stars
3 watching
7 forks
Language: Python
last commit: almost 2 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| | Enables collaboration between AI agents to solve tasks and interact with each other | 1,171 |
| | An autonomous agent framework for controlling real-world applications via RESTful APIs using large language models | 1,328 |
| | A tool for deploying and managing autonomous AI agents in a web-based interface | 184 |
| | An open-source multi-agent simulation framework using GPT-4 to explore AI-powered collaboration and task execution | 1,647 |
| | A global proxy agent configurable using environment variables. | 365 |
| | An AI-powered search assistant for developers to find code and workspace information quickly. | 2,021 |
| | Automates repetitive browser actions using natural language prompts and GPT-4 | 1,034 |
| | An agent for managing control plane operations in VPP-based network functions | 253 |
| | Enables OpenAI GPT to process multimedia inputs like images and audio with text output | 184 |
| | A custom PPO agent for autonomous driving in CARLA. | 231 |
| | An open-source platform for developing and testing AI-powered game agents | 79 |
| | An autonomous driving project exploring the capabilities of a visual-language model in understanding complex driving scenes and making decisions | 288 |
| | An AI-powered developer assistant tool for semi-autonomous coding and file system tasks using OpenAI's GPT-4 model. | 169 |
| | An open source software project that extends the functionality of Xiaomi gateways | 29 |
| | Provides an API and environment for training AI agents in Unity, using the Unity ML-Agents package | 3 |