AI Agents Frameworks

Adala is an Autonomous DAta (Labeling) Agent framework. Adala offers a robust framework for implementing agents specialized in data processing, with an emphasis on diverse data labeling tasks. These agents are autonomous, meaning they can independently acquire one or more skills through iterative learning. This learning process is influenced by their operating environment, observations, and reflections. Users define the environment by providing a ground truth dataset. Every agent learns and applies its skills in what we refer to as a "runtime", synonymous with LLM.

Useful general intelligence At Adept, we are building a future where AI helps every employee focus on meaningful work. We envision a workplace where our time is mainly spent on collaboration, creativity, and strategic decision-making. In today's digital landscape, Adept seamlessly integrates into existing workflows and business processes, executing tasks across the software tools and systems employees use every day. Powered by our best-in-class proprietary model, our tool navigates systems to extract, transform, and populate information into forms, websites, and SaaS applications reliably at scale, all while adhering to a company’s business rules and processes. With Adept completing these manual, repetitive workflows, employees can use the gift of time to focus on more strategic work. Companies can rest easy knowing that processes are being executed exactly the way they want, every time. Adept is the enterprise AI tool that powers your workforce.

Reliable agent framework built on top of OpenAI Assistants API. (Responses API soon)

Handy AI Components for Developers. Seamlessly build custom RAG flows and AI agents using open-source, copy-paste components.

Your Open-Source AI Companion. Limitless, Transparent, and Entirely Yours.

AgentForge: Open Source AI Agent Framework for Building Cognitive Architectures AgentForge is an open-source framework designed to simplify the process of developing intelligent agents. Whether you're working on autonomous systems, task automation, or research projects, AgentForge provides a robust and modular foundation for creating agents that can perceive, reason, and act independently. What is AgentForge? At its core, AgentForge is a framework for building and managing intelligent agents. It provides developers with a structured environment to define agent behavior, manage workflows, and integrate various components without the need to reinvent the wheel. AgentForge offers a streamlined approach to building agents that work the way you want them to. The framework is designed to be flexible and extensible, allowing users to tailor their agents to meet specific requirements. The framework emphasizes modularity and customization, allowing you to assemble agents from reusable components rather than starting from scratch each time. Why We Built It The world of AI agents is evolving rapidly, but building effective, reliable agents remains challenging. We created AgentForge to democratize agent development and give developers the tools to experiment, iterate, and deploy without getting bogged down in boilerplate code or complex architectures. Getting Started AgentForge makes it simple to define your agent's capabilities, memory systems, and decision-making processes. The framework handles the complex orchestration between components, letting you focus on what makes your agent effective. Core Architecture AgentForge's architecture is built around a flexible component system that allows developers to mix and match different functional modules. Our directory structure reflects this modular approach, with clear separation between agents, tools, personas, and supporting infrastructure. Agents Module The Agents module forms the heart of AgentForge, providing the foundational structures for creating intelligent autonomous agents. We've designed this system to be both powerful and accessible, allowing developers to: Create agents with different cognitive capabilitie Configure memory systems for contextual awareness Define specialized agent roles for specific domains Implement multi-agent coordination for complex tasks Per-prompt LLM setting overrides Our agent architecture supports both simple reactive agents and sophisticated planning-based agents, depending on your application requirements. The modular design allows you to start simple and incrementally add complexity as your project evolves. Persona System One of our most distinctive features is the Persona system, which allows agents to adopt different interaction styles and behaviors. This system enables: Creating agents with consistent personalities Designing specific communication styles for different user needs Implementing role-based behaviors for specialized tasks Maintaining context-appropriate responses across interactions The Persona system is particularly valuable for customer-facing applications where the agent's communication style significantly impacts user experience. Tools and Actions Framework Our ToolsAndActions module provides a comprehensive library of capabilities that agents can leverage, including: Text processing and natural language understanding Data analysis and transformation function Web browsing and information retrieval File system operations and document processing Mathematical and logical reasoning capabilities These tools can be combined in novel ways, allowing agents to solve complex problems by chaining together simpler operations. The framework handles tool execution, error handling, and result processing automatically. Join the Community We're building AgentForge in the open, and we'd love for you to be part of the journey. Check out our website at agentforge.net for more information, or join our Discord Community and connect with the developers. Whether you're looking to automate tasks, create interactive experiences, or explore the frontiers of agent-based AI, we hope AgentForge provides the tools you need to bring your ideas to life. Happy building!

AgentKit: rapidly build high quality Agent apps AgentKit is a LangChain-based starter kit developed by BCG X to build Agent apps. Developers can use AgentKit to Quickly experiment on your constrained agent architecture with a beautiful UI Build a full stack chat-based Agent app that can scale to production-grade MVP Key advantages of the AgentKit toolkit include: 🚀 Quickly build high quality Agent apps: Build a strong demo in a few hours using a modular, easy to configure tech stack based on FastAPI/Nextjs and a library of useful GenAI tools 💻 Flexible, reactive UI/UX designed for Agents: React/Nextjs chat-based UI that is easy to configure, with features such as streaming, rendering of tables/visualizations/code, status of Agent actions and more 🛡️ Focus on reliability: Easy to configure routing architecture gives control of possible paths Agent can take, increasing reliability and making it suited for real-life use cases 📈 Set up to scale: Set up to scale to MVP with ready made Queue Management, Auth, Caching, Monitoring etc.

RAG for Developers. The open-source RAG platform. Fully performant and with agentic superpowers.

AI Agents Powered by You. Build and manage AI agents effortlessly—no code, fully modular, and open to all. Agience helps you build AI agents to automate tasks, streamline workflows, and integrate with any LLM, cloud, or AI service. Our open-source platform ensures secure, scalable, and private automation with modular AI tools.

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

Agno is a full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning. Engineers and researchers use Agno to build the 5 levels of Agentic Systems: Level 1: Agents with tools and instructions (example). Level 2: Agents with knowledge and storage (example). Level 3: Agents with memory and reasoning (example). Level 4: Agent Teams that can reason and collaborate (example). Level 5: Agentic Workflows with state and determinism (example).

Multimodal Agents as Smartphone Users.

AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.

Welcome to AutoGPT, where AI amplifies human potential. Our platform empowers you to create intelligent assistants that streamline your digital workflow, enabling you to dedicate more time to innovative and impactful pursuits.

Introducing Aviator Agents An LLM-based Agentic framework to perform large scale code migrations in your repositories. Aviator Agents integrates directly with GitHub and supports Open-AI o1, Claude Sonnet 3.5, Llama 3.1, DeepSeek R1 models. ‍ • Perform small or large scale migrations across your code base • Break down large PRs using smart context, or code ownership • Plan out custom steps to perform a task using multi-agent approach • Analyze the build results to verify and iterate • Perform actions across your code base or inside a specified package