Discover Agentic AI in the AI Agent Development Frameworks category: Comprehensive directory of solutions with open-source code verified by AI agency professionals.

Open-Source Agentic AI in "AI Agent Development Frameworks" Category

Agent Network Protocol (ANP) is an open-source communication protocol designed to facilitate secure, decentralized interactions among AI agents. It aims to become the 'HTTP of the Agentic Web Era' by providing a standardized framework that enables agents to connect, communicate, and collaborate efficiently. ANP's architecture comprises three layers: the Identity Layer for decentralized authentication using W3C DID standards, the Meta-Protocol Layer for dynamic protocol negotiation, and the Application Layer for semantic-based capability descriptions. This structure ensures interoperability, scalability, and secure communication across diverse AI systems.

Agent Network Protocol

agent-network-protocol

An open-source protocol enabling secure, decentralized communication among AI agents.

Google's Agent Development Kit (ADK) is an open-source framework designed to simplify the creation, deployment, and management of AI agents. Optimized for Google's Gemini models yet model-agnostic, ADK supports various agent types, including LLM-powered agents, workflow controllers, and custom agents. It offers features like multi-agent orchestration, tool integration, session management, and built-in evaluation tools. ADK facilitates flexible deployment options, including local environments, Google Cloud's Vertex AI Agent Engine, and Cloud Run, making it suitable for a wide range of AI applications.

Google Agent Development Kit

google-agent-development-kit

A modular framework for building, deploying, and managing AI agents across diverse workflows.

Google's Agent2Agent (A2A) protocol is an open standard designed to facilitate seamless communication and collaboration between AI agents developed by different organizations using various frameworks. A2A provides a standardized method for agents to discover each other's capabilities, negotiate interaction modalities, and securely collaborate on tasks without exposing internal states or proprietary tools. Built on existing technologies like HTTP, JSON-RPC 2.0, and Server-Sent Events (SSE), A2A supports both synchronous and asynchronous interactions, enabling agents to handle complex, long-running tasks efficiently. The protocol emphasizes security, interoperability, and scalability, making it suitable for enterprise-grade applications.

Google A2A

google-a2a

An open protocol enabling AI agents to communicate and collaborate across diverse systems securely.

Cerebrum is the Software Development Kit (SDK) for AIOS, the AI Agent Operating System. It provides developers with tools to build, deploy, and manage large language model (LLM)-based AI agents. Cerebrum addresses challenges such as scheduling, context switching, memory management, and tool integration, facilitating the creation of efficient and scalable AI agents. The SDK features a modular architecture encompassing LLM, memory, storage, and tool management layers, and includes an Agent Hub for sharing and discovering agents with version control and dependency management.

Cerebrum: AIOS SDK

cerebrum-aios-sdk

An SDK for developing and deploying LLM-based AI agents within the AIOS framework.

Apple's Ferret-UI is a multimodal large language model (MLLM) designed to comprehend and interact with mobile user interfaces (UIs). It possesses referring, grounding, and reasoning capabilities, enabling it to identify UI elements such as icons and text, understand their spatial relationships, and execute tasks based on this understanding. Ferret-UI aims to improve user interactions by facilitating advanced control over devices through natural language commands, potentially enhancing accessibility and automation in mobile applications.

Apple Ferret-UI

apple-ferret-ui

A multimodal AI model for enhanced understanding and interaction with mobile user interfaces.

The Capability Collaboration based AI Agent (CACA Agent) is an AI system designed to enhance the extensibility and functionality of AI agents by integrating a set of collaborative capabilities. Inspired by service computing, it reduces reliance on a single large language model (LLM) and promotes an open architecture. CACA Agent introduces components such as Planning Capability, Methodology Capability, Tools Capability, Tool Broker, and Tool Service, which work together to provide AI agent functionalities. This design facilitates quick deployment of AI agents and convenient expansion of their application scenarios, allowing for dynamic tool integration and improved planning abilities. A demonstration of the system illustrates its operation and the extension of application scenarios.

CACA Agent

caca-agent

An AI system enhancing agent extensibility through collaborative capabilities.

PC Agent is an AI system developed by GAIR-NLP that facilitates the creation of autonomous digital agents by transferring human cognitive processes. It comprises three key components: PC Tracker, a lightweight infrastructure for collecting large-scale human-computer interaction data; a Cognition Completion post-processing pipeline that converts raw interaction data into cognitive trajectories; and a multi-agent system combining a planning agent for decision-making with a grounding agent for robust visual grounding. PC Agent aims to enable AI to perform complex digital tasks autonomously by learning from human interactions.

PC Agent

pc-agent

An AI system enabling autonomous digital agents through human cognition transfer.

Awesome MCP Servers is a GitHub-curated list compiling various MCP (Model Context Protocol) servers that allow large language models to interface with external tools, files, APIs, databases, and more. These servers empower AI agents to perform tasks beyond simple text generation by enabling them to access structured resources and execute contextual operations. The list features both production-ready and experimental implementations contributed by the community.

Awesome MCP Servers

awesome-mcp-servers

A curated list of Model Context Protocol (MCP) servers enhancing AI capabilities with external tools and data.

kagent is an open-source framework designed for DevOps and platform engineers to deploy and manage AI agents within Kubernetes environments. It provides predefined tools for AI agents to interact with cloud-native projects like Kubernetes, Prometheus, Istio, Argo, and Helm. These autonomous agents are capable of planning, executing tasks, analyzing results, and continuously improving outcomes, thereby automating complex operations and troubleshooting tasks in cloud-native operations.

kagent

An open-source framework enabling AI agents to automate Kubernetes operations.

Giselle is an open-source platform that empowers teams to design and deploy advanced AI agents using an intuitive node-based interface. By integrating multiple large language models (LLMs) and data sources, Giselle facilitates the automation of complex tasks such as market research and code reviews. Its visual development environment simplifies the creation of sophisticated AI workflows, making AI accessible to all team members and enhancing productivity through seamless human-AI collaboration.

Giselle

giselle

An open-source platform enabling teams to create AI agents through a visual node-based interface for automating complex workflows.

Gemma 3 is Google's latest open-source AI model, designed to run efficiently on a single GPU or TPU. It supports multimodal inputs, including text, images, and short videos, and offers advanced reasoning capabilities. With support for over 140 languages and a 128k-token context window, Gemma 3 is versatile for various applications. Its quantized versions enhance performance and reduce computational requirements, making it accessible for devices ranging from smartphones to workstations.

Gemma 3

gemma-3

An open-source AI model optimized for single-GPU performance, supporting multimodal inputs and over 140 languages.

L2MAC (Large Language Model Automatic Computer) is an AI framework designed to generate extensive outputs, such as entire codebases or lengthy texts, from a single prompt. It employs a multi-agent system where each agent executes a portion of the task, effectively bypassing the fixed context window constraints of traditional LLMs. This approach allows L2MAC to produce coherent and large-scale outputs, significantly enhancing the capabilities of AI in software development and content creation.

L2MAC

l2mac

An AI framework enabling large-scale code generation by overcoming LLM context limitations.

Open-Source Agentic AI Category "AI Agent Development Frameworks"