Communicative Agents for "Mind" Exploration of Large Language Model Society
Cross-environment Agent Benchmark for Multimodal Language Model Agents
Can Large Language Model Agents Simulate Human Trust Behaviors?
Open Agents Social Interaction Simulations on a Large Scale
|
CAMEL-AI.org is the 1st LLM multi-agent framework and an open-source community dedicated to finding the scaling law of agents.
We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks.
Rigorous research takes time and resources. With advanced GPU access and a dedicated team, we explore the frontier research topics by balancing urgency and patience. Join our ongoing projects or test new ideas with us, reach out via email for more information.
We value every contribution, from new features to bug fixes. Projects at CAMEL evolves around enhancing infrastructure, improving documentation, and implementing research ideas. Check out our Contributing Guidelines on GitHub.
These power your agents
The core entities that perform tasks
Enhance your agents' capabilities
Enable agents to retain and utilize information
Instructions that guide your agents
Improve LLM accuracy by 50% or more with Log10's AutoFeedback. Scale human perspective by 1000x using fine-tuned models and synthetic data.
AI Geometric is your AI-powered interview co-pilot, transforming job preparation from a solo task into an immersive, multi-dimensional experience.
Empower your AI agents with Composio - a platform for managing and integrating tools with LLMs & AI agents using Function Calling.
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
“The thing that I find really interesting with this is that it’s an unbelievably good way to make synthetic data. If you’re trying to create any sort of customer service or chatbot agent that communicates with the public, this allows you to make synthetic data for training and fine-tuning.”
.png){kind=avatar}
"The CAMEL AI “Domain Expert” dataset, comprising 25,000 conversations between two GPT 3.5 Turbo agents was used as part of the training data for Teknium’s OpenHermes model and the Microsoft Phi model"
"Guohao Li, who designed Camel, highlights the potential of multi-agent systems to bypass traditional AI limitations, enabling tasks like phishing email generation and cyber bug development."
.jpg){kind=avatar}
“The essence of Camel lies in its prompt engineering, i.e., inception prompting. The prompts are actually carefully defined to assign roles, prevent flipping roles, prohibit harm and false information, and encourage consistent conversation.”
MPT-30B-Chat is a chatbot-like model for dialogue generation. It was built by finetuning MPT-30B and trained on 19.54% Camel-AI sourced data
"This innovative concept is set to redefine the way AI agents interact with each other and, in doing so, revolutionize the realm of conversational AI."
.jpg)
