Base OnChain Agent is an open-source framework designed to deploy autonomous AI agents on Ethereum-like blockchains. It connects to blockchain nodes via Web3 and uses OpenAI's GPT models to interpret on-chain events such as token transfers or protocol-specific logs. The agent can process natural language prompts or predefined strategies to decide when to execute transactions, call smart contract functions, or respond to governance proposals. Developers can extend modules for custom event listeners, integrate off-chain data feeds, and manage private keys securely. This solution enables automated DeFi operations like liquidity provisioning, arbitrage trading, and portfolio rebalancing with minimal manual intervention.

Cerebellum offers a modular platform where developers define agents using declarative plans composed of sequential steps or tool invocations. Each plan can call built-in or custom tools—such as API connectors, retrievers, or data processors—through a unified interface. Memory modules allow agents to store, retrieve, and forget information across sessions, enabling context-aware and stateful interactions. It integrates with popular LLMs (OpenAI, Hugging Face), supports custom tool registration, and features an event-driven execution engine for real-time control flow. With logging, error handling, and plugin hooks, Cerebellum boosts productivity, facilitating rapid agent development for automation, virtual assistants, and research applications.

Thousand Birds is an extensible AI agent framework allowing developers to define and configure agent behaviors using a Python SDK and CLI. Agents can plan multi-step workflows, integrate web search, interact with browser sessions, read and write files, call external APIs, and manage stateful memory. It supports plugin modules to add custom tools and data connectors. The built-in orchestration engine schedules tasks, handles retries, and logs execution details. Developers can chain agents, enable parallel execution, and monitor performance through structured outputs. Thousand Birds accelerates deployment of autonomous assistants for research, data extraction, automation, and experimental prototypes.

Coffee-Shop-AI-Agents is an open-source framework for building and deploying specialized AI agents that automate key coffee shop functions. Leveraging LangChain and OpenAI models, the project provides modular agents, including a barista agent that handles complex beverage orders, offers customization recommendations, and manages ingredient availability. The cashier agent processes payments, issues digital receipts, and tracks sales metrics. A manager agent generates inventory forecasts, suggests restocking schedules, and analyzes performance data. With customizable prompts and pipeline configurations, developers can quickly adapt the agents to unique shop policies and menu items. The repository includes setup scripts, API integrations, and example workflows to simulate realistic customer interactions and operational analytics in a developer-friendly environment.

DeepMind MAS Environment is a Python library that provides a standardized interface for building and simulating multi-agent reinforcement learning tasks. It allows users to configure number of agents, define observation and action spaces, and customize reward structures. The framework supports agent-to-agent communication channels, performance logging, and rendering capabilities. Researchers can seamlessly integrate DeepMind MAS Environment with popular RL libraries such as TensorFlow and PyTorch to benchmark new algorithms, test communication protocols, and analyze both discrete and continuous control domains.

Devon provides a comprehensive suite of tools for defining, orchestrating, and running autonomous agents within Python applications. Users can outline agent goals, specify callable tasks, and chain actions based on conditional logic. Through seamless integration with language models like GPT and local vector stores, agents ingest and interpret user inputs, retrieve contextual knowledge, and generate plans. The framework supports long-term memory via pluggable storage backends, enabling agents to recall past interactions. Built-in monitoring and logging components allow real-time tracking of agent performance, while a CLI and SDK facilitate rapid development and deployment. Suitable for automating customer support, data analysis pipelines, and routine business operations, Devon accelerates the creation of scalable digital workers.

FastMCP is an open-source Python framework for building MCP (Model Context Protocol) servers and clients that empower LLMs with external tools, data sources, and custom prompts. Developers define tool classes and resource handlers in Python, register them with the FastMCP server, and deploy using transport protocols like HTTP, STDIO, or SSE. The framework’s client library offers an asynchronous interface for interacting with any MCP server, facilitating seamless integration of AI agents into applications.

Joylive Agent offers a modular, plugin-based architecture tailored for building sophisticated AI agents. It provides seamless integration with LLMs such as OpenAI GPT, configurable memory backends for session persistence, and a toolkit manager to expose external APIs or custom functions as agent capabilities. The framework also includes built-in chain-of-thought orchestration, multi-turn dialogue management, and a RESTful server for easy deployment. Its Java core ensures enterprise-grade stability, allowing teams to rapidly prototype, extend, and scale intelligent assistants across various use cases.

LAWLIA provides a structured interface to define agent behaviors, plugin tools, and memory management for conversational or autonomous workflows. Developers can integrate with major LLM APIs, configure prompt templates, and register custom tools like search, calculators, or database connectors. Through its Agent class, LAWLIA handles planning, action execution, and response interpretation, allowing multi-turn interactions and dynamic tool invocation. Its modular design supports extending capabilities via plugins, enabling agents for customer support, data analysis, code assistance, or content generation. The framework streamlines agent development by managing context, memory, and error handling under a unified API.

MDLR is an innovative, open-source framework that utilizes AI to analyze and organize unstructured content like comments and notes. This powerful platform helps transform scattered data into actionable, real-time, and continually evolving summaries. Ideal for personal diaries and collaborative efforts, MDLR provides users with AI-driven summaries that adapt as new data is introduced, ensuring insights remain current and relevant. Easily integrated into various platforms, MDLR enhances project management with auto-updating notes and summaries, perfect for both individual and group usage.

Multi-Agent-Seller provides a modular environment for simulating e-commerce negotiations using AI agents. It includes pre-built buyer and seller agents with customizable negotiation strategies, such as dynamic pricing, time-based concessions, and utility-based decision-making. Users can define custom protocols, message formats, and market conditions. The framework handles session management, offer tracking, and result logging with built-in visualization tools for analyzing agent interactions. It integrates easily with machine learning libraries for strategy development, enabling experimentation with reinforcement learning or rule-based agents. Its extensible architecture allows adding new agent types, negotiation rules, and visualization plugins. Multi-Agent-Seller is ideal for testing multi-agent algorithms, studying negotiation behaviors, and teaching concepts in AI and e-commerce domains.

OpenSilver is a free, open-source UI framework designed for building modern .NET web applications using C# and XAML. It supports WPF and Silverlight applications and facilitates seamless transition away from legacy Silverlight technology. The framework ensures 100% code reusability, compatibility with various modern web technologies like Blazor, React, and Angular, and offers an AI-enhanced XAML designer for Visual Studio Code. With OpenSilver, developers can build cross-platform applications that run on any browser and device, preserving the original look and feel of the apps, while significantly reducing the migration cost and time.

PerfAgents is an AI-powered synthetic monitoring and testing platform designed to simplify the setup and management of monitoring your critical applications. It supports multiple open-source frameworks like Selenium, Puppeteer, Cypress, and Playwright. By leveraging your existing scripts or effortlessly creating new ones, PerfAgents provides continuous testing, reducing downtime and ensuring optimal application performance. It seamlessly integrates with tools like Slack, Microsoft Teams, Jira, and PagerDuty for real-time alerts and notifications.

Promptix Python is an open-source framework for building autonomous AI agents in Python. With a simple installation via pip, you can instantiate agents powered by any major LLM, register domain-specific tools, configure in-memory or persistent data stores, and orchestrate multi-step decision loops. The SDK supports real-time streaming of token outputs, callback handlers for logging or custom processing, and built-in memory modules to retain context across interactions. Developers can leverage this library to prototype chatbot assistants, automations, data pipelines, or research agents in minutes. Its modular design allows swapping models, adding custom tools, and extending memory backends, providing flexibility for a wide range of AI agent use cases.

SoccerAgent is a specialized AI framework designed for developing and training autonomous soccer agents using state-of-the-art multi-agent reinforcement learning (MARL) techniques. It simulates realistic soccer matches in 2D or 3D environments, offering tools to define reward functions, customize player attributes, and implement tactical strategies. Users can integrate popular RL algorithms (such as PPO, DDPG, and MADDPG) via built-in modules, monitor training progress through dashboards, and visualize agent behaviors in real time. The framework supports scenario-based training for offense, defense, and coordination protocols. With an extensible codebase and detailed documentation, SoccerAgent empowers researchers and developers to analyze team dynamics and refine AI-driven gameplay strategies for academic and commercial projects.

Step Functions Agent is an open-source toolkit enabling developers to construct intelligent serverless workflows on AWS. By leveraging Large Language Models like OpenAI's GPT, this agent dynamically generates AWS Step Functions state machine definitions based on natural language prompts or structured instructions. It supports invoking Lambda functions, passing context between steps, implementing conditional branching, parallelization, retries, and error handling. The framework abstracts AWS service integrations, automatically provisions resources, and offers observability through CloudWatch. Users can customize prompts, integrate custom functions, and monitor workflow executions. With built-in fallback strategies and audit logging, Step Functions Agent streamlines building scalable, resilient AI-driven automation pipelines, accelerating development for data processing, ETL, and decision support applications.

VMAS is a comprehensive toolkit for building and training multi-agent systems using deep reinforcement learning. It supports GPU-based parallel simulation of hundreds of environment instances, enabling high-throughput data collection and scalable training. VMAS includes implementations of popular MARL algorithms like PPO, MADDPG, QMIX, and COMA, along with modular policy and environment interfaces for rapid prototyping. The framework facilitates centralized training with decentralized execution (CTDE), offers customizable reward shaping, observation spaces, and callback hooks for logging and visualization. With its modular design, VMAS seamlessly integrates with PyTorch models and external environments, making it ideal for research in cooperative, competitive, and mixed-motive tasks across robotics, traffic control, resource allocation, and game AI scenarios.

Cloudflare Agents is designed to help developers build, deploy, and manage autonomous AI agents at the network edge using Cloudflare Workers. By leveraging a unified SDK, you can define agent behaviors, custom actions, and conversational flows in JavaScript or TypeScript. The framework seamlessly integrates with major LLM providers like OpenAI and Anthropic, and offers built-in support for HTTP requests, environment variables, and streaming responses. Once configured, agents can be deployed globally in seconds, providing ultra-low latency interactions to end-users. Cloudflare Agents also includes tools for local development, testing, and debugging, ensuring a smooth development experience.

Autonomous Economic Agents (AEA) by Fetch.ai is a versatile framework that empowers developers to design, implement, and orchestrate autonomous software agents capable of interacting with each other, external environments, and digital ledgers. Leveraging a plugin-based architecture, AEA provides pre-built modules for communication protocols, cryptographic ledger APIs, decentralized identity, and customizable decision-making skills. Agents can discover and transact within decentralized marketplaces, perform goal-driven behaviors, and adapt through real-time data feeds. The framework supports simulation tools for testing and debugging multi-agent scenarios, as well as deployment onto live blockchains or peer-to-peer networks. With built-in interoperability and agent-to-agent messaging, AEA streamlines the development of complex autonomous economic applications such as energy trading, supply chain optimization, and smart IoT coordination.

AAGPT is an extensible, open-source AI agent framework designed for building autonomous agents. It enables you to define high-level objectives, manage conversational memory, plan multi-step tasks, and integrate external tools or APIs. Using a simple configuration file and Python SDK, you can customize agent behavior, define custom actions, and deploy agents that can interact with data sources, execute commands, and learn from past interactions to improve performance over time.