CAMEL-AI is a open-source community for finding the scaling laws of agents for data generation, world simulation, task automation.
We believe that studying intelligent agents and multi-agent systems agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks.
Join Research MeetingRigorous research takes time and resources. We are a community-driven research collective with 100+ researchers exploring the frontier research of Multi-agent Systems and intelligent agents for real-world automation. 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, building robust multi‑agent systems, generating synthetic data pipelines, and implementing research ideas. Check out our Contributing Guidelines on GitHub.
CAMEL is the world's first multi-agent system. It is designed to be data-driven, stateful, and agent-friendly.
Matrix is a social media simulation platform built with OASIS that blends real-time trending posts with precise user agent behavior simulation. It supports marketers in running A/B tests and simulates user feedback.
EigentBot deploys an AI-powered community manager in seconds! - Seamlessly integrate with web links, files, Notion, GitHub, LinkedIn, and more. - Prioritizing privacy, we support local model deployment. - With one-click, get your bot running in just 3 seconds!
Mistral AI focuses on creating efficient, cost-effective AI models that require fewer computational resources. The company offers both free open-source models and commercial API-only models, aiming to democratize AI technology
It offers enterprise-scale AI platforms, including hardware and software, designed for generative AI. SambaNova's products feature proprietary chip designs and full-stack approaches, enabling efficient deployment of complex AI applications across various industries.
Qdrant offers a high-performance, open-source vector search database designed to power next-generation AI applications. It enables efficient similarity searches for high-dimensional data, facilitating tasks like matching, searching, and recommending.
Empower your AI agents with Composio - a platform for managing and integrating tools with LLMs & AI agents using Function Calling.
Firecrawl turns entire websites into clean, LLM-ready markdown or structured data. Scrape, crawl and extract the web with a single API.
Milvus is an open-source vector database built for GenAI applications. Install with pip, perform high-speed searches, and scale to tens of billions of vectors with minimal performance loss.
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
ChatEval is a scalable evaluation framework that combines automated metrics and human judgments to benchmark and improve chatbots’ dialogue quality.
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.
“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.”
.avif){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)
