Olas is a decentralized platform that democratizes AI ownership by enabling individuals to run autonomous AI agents and participate in agent economies. Through its open-source framework, Olas facilitates the development and deployment of AI agents that operate across multiple blockchains. Participants can earn OLAS tokens by running agents, contributing to the ecosystem, and engaging in various roles such as developers, operators, and governors. Olas aims to create a collaborative environment where AI technologies are accessible and beneficial to all.

Olas

olas

A platform enabling co-ownership of AI through autonomous agent economies, allowing individuals to run AI agents and earn rewards.

Griptape is a modular open-source Python framework that enables developers to build and deploy AI-powered applications utilizing large language models (LLMs). It provides clean and clear abstractions for creating agents, pipelines, workflows, and retrieval-augmented generation (RAG) implementations without extensive prompt engineering. Griptape's composability makes it ideal for developing conversational and event-driven AI applications that can access and manipulate data securely and reliably. The framework supports integration with various data sources and APIs, facilitating the development of scalable and efficient AI solutions.

Griptape

griptape

A modular open-source Python framework for building and deploying LLM-based agents, pipelines, and workflows.

The Internet of Agents (IoA) is an open-source framework that emulates the Internet's architecture to enable seamless collaboration among diverse AI agents operating in various environments. By introducing an agent integration protocol and an instant-messaging-like architecture, IoA allows agents to form autonomous nested teams, manage asynchronous tasks, and adapt conversation flows dynamically. This design enhances the scalability and flexibility of multi-agent systems, promoting efficient problem-solving through collaborative intelligence.

Internet of Agents

internet-of-agents

An open-source framework inspired by the Internet, designed to facilitate collaboration among heterogeneous AI agents across diverse environments.

ChatDev is an open-source framework that simulates a virtual software company, employing intelligent agents powered by large language models (LLMs) to automate the software development lifecycle. By adopting a waterfall model, ChatDev divides the process into distinct phases—designing, coding, testing, and documentation—with specialized agents collaborating in each phase. This approach enables the rapid and cost-effective generation of complete software applications, including source code, user manuals, and environmental dependencies. ChatDev's innovative use of multi-agent systems and natural language communication streamlines development workflows, reduces errors, and enhances efficiency.

ChatDev

chatdev

An open-source framework utilizing large language models to automate the entire software development process through multi-agent collaboration.

GPTSwarm is an open-source framework that models language agents as computational graphs, enabling the development, integration, and automatic optimization of various LLM-based agents. Each node within the graph represents a function to process multimodal data or query other LLMs, while edges define the information flow between operations and agents. This structure allows for the creation of composite graphs representing hierarchies of inter-agent collaboration. GPTSwarm introduces automatic graph optimizers that refine node-level LLM prompts and improve agent orchestration by modifying graph connectivity, thereby enhancing the efficiency and effectiveness of AI-driven problem-solving.

GPTSwarm

gptswarm

An open-source framework representing language agents as optimizable graphs to enhance problem-solving with Large Language Models.

AutoGen is an open-source programming framework developed by Microsoft for constructing AI agent systems. It streamlines the development of event-driven, distributed, scalable, and resilient agentic applications, enabling the creation of systems where AI agents collaborate to perform tasks autonomously or with human oversight. AutoGen supports asynchronous message passing between agents, integration of large language models (LLMs), and advanced multi-agent design patterns, facilitating the orchestration, automation, and optimization of complex LLM workflows.

AutoGen

autogen

An open-source framework for building AI agent systems, simplifying the creation of event-driven, distributed, scalable, and resilient agentic applications.

PraisonAI is an open-source framework that integrates AutoGen and CrewAI, or similar frameworks, into a low-code solution for developing and orchestrating multi-agent large language model (LLM) systems. It focuses on ease of use, customization, and effective human-agent interaction, enabling users to create AI-powered multi-agent systems for various applications, including customer service, personalization, chatbots, automation, and analysis. PraisonAI supports features such as real-time voice interaction, internet search capabilities, and vision language model support, making it a versatile tool for AI development.

PraisonAI

praisonai

An open-source, low-code framework for building and managing multi-agent LLM systems, emphasizing simplicity, customization, and efficient human-agent collaboration.

CRAB (Cross-environment Agent Benchmark) is an open-source framework developed by CAMEL-AI for constructing and evaluating environments designed for large language model (LLM) agents. It supports the creation of cross-platform environments, enabling deployment across in-memory systems, Docker-hosted environments, virtual machines, or distributed physical machines. CRAB introduces a graph-based fine-grained evaluation method and an efficient mechanism for task and evaluator construction, facilitating comprehensive assessment of agent performance across diverse settings.

CRAB: Cross-environment Agent Benchmark

crab-cross-environment-agent-benchmark

An open-source framework for building and benchmarking environments tailored for large language model (LLM) agents across multiple platforms.

FastAgency is an open-source framework designed to streamline the transition of multi-agent AI workflows from prototype to production. It offers a unified programming interface compatible with various agentic AI frameworks, enabling developers to deploy agentic workflows in both development and production settings. With features like multi-runtime support, seamless external API integration, and a command-line interface for orchestration, FastAgency simplifies the creation of scalable, production-ready architectures for serving AI workflows.

FastAgency

fastagency

An open-source framework that accelerates the deployment of multi-agent AI workflows from prototype to production.

LAgent is a lightweight, open-source Python framework designed to facilitate the development of agents powered by large language models (LLMs). It offers a modular architecture that allows users to efficiently build, customize, and deploy LLM-based agents for various applications. The framework provides typical tools to augment LLM capabilities, enabling functionalities such as code execution, data analysis, and predictive modeling. Inspired by the design philosophy of PyTorch, LAgent emphasizes clear workflows and intuitive agent construction, making it accessible for both novice and experienced developers.

LAgent

lagent

An open-source framework for building large language model-based agents with modular components and tool integration.

Explore AI Agents Tagged with "open-source framework"