CodeFuse-muAgent is a Python-based open-source framework that orchestrates multiple autonomous AI agents to collaboratively solve complex tasks. Developers define individual agents with specialized skills—such as data processing, natural language understanding, or external API interaction—and configure communication protocols for dynamic task delegation. The framework provides centralized memory management, logging, and monitoring, while remaining model-agnostic, supporting integration with popular LLMs and custom AI models. By leveraging CodeFuse-muAgent, teams can build modular AI workflows, automate multi-step processes, and scale deployments across diverse environments. Flexible configuration files and extensible APIs enable rapid prototyping, testing, and fine-tuning, making it suitable for use cases in customer support, content generation pipelines, research assistants, and more.

The Contract Net Protocol repository provides a full Java implementation of the FIPA Contract Net interaction protocol. Developers can create manager and contractor agents that exchange CFP (Call For Proposal), proposals, acceptances, and rejections over agent communication channels. The code includes core modules for broadcasting tasks, collecting bids, evaluating proposals based on customizable criteria, awarding contracts, and monitoring execution status. It can be integrated into larger multi-agent frameworks or used as a standalone library for research simulations, industrial scheduling, or robotic coordination.

DialSense offers a robust suite of tools for building, training, and managing voice assistants, providing a centralized solution for businesses looking to enhance consumer interactions. With an array of impressive features, that include customizable conversational bots and auto-scaling capabilities, it simplifies the process of voice assistant management. Request a demo today to see how DialSense can transform your business communication strategies.

LangGraph Agent combines LLMs with a graph-structured memory to build autonomous agents that can remember facts, reason over relationships, and call external functions or tools when needed. Developers define memory schemas as graph nodes and edges, plug in custom tools or APIs, and orchestrate agent workflows through configurable planners and executors. This approach enhances context retention, enables knowledge-driven decision making, and supports dynamic tool invocation in diverse applications.

The project uses the JADE (Java Agent DEvelopment) framework to build a multi-agent environment. It defines agents that register with the platform’s AMS and DF, exchange ACL messages, and execute behaviors like cyclic, one-shot, and FSM. Example scenarios include buyer-seller negotiations, contract net protocols, and task allocation. A GUI agent container helps monitor runtime agent states and message flows.

Camel AI is an open-source framework designed to simplify the creation and orchestration of intelligent agents. It offers abstractions for chaining large language models, integrating external tools and APIs, managing knowledge graphs, and persisting memory. Developers can define multi-agent workflows, decompose tasks into subplans, and monitor execution through a CLI or web UI. Built on Python and Docker, Camel AI allows seamless swapping of LLM providers, custom tool plugins, and hybrid planning strategies, accelerating development of automated assistants, data pipelines, and autonomous workflows at scale.

Super-Agent-Party allows developers to define a Party object where individual AI agents perform distinct roles such as planning, researching, drafting, and reviewing. Each agent can be configured with custom prompts, tools, and model parameters. The framework manages message routing and shared context, enabling agents to collaborate in real time on subtasks. It supports plugin integration for third-party services, flexible agent orchestration strategies, and error handling routines. With an intuitive API, users can dynamically add or remove agents, chain workflows, and visualize agent interactions. Built on Node.js and compatible with major cloud providers, Super-Agent-Party streamlines the development of scalable, maintainable AI multi-agent systems for automation, content generation, data analysis, and more.

SwarmFlow enables developers to instantiate and coordinate a swarm of AI agents using configurable workflows. Agents can asynchronously exchange messages, delegate sub-tasks, and integrate custom plugins for domain-specific logic. The framework handles task scheduling, result aggregation, and error management, allowing users to focus on designing agent behaviors and collaboration strategies. SwarmFlow’s modular architecture simplifies building complex pipelines for automated brainstorming, data processing, and decision support systems, making it easy to prototype, scale, and monitor multi-agent applications.

AgentsForce is an advanced AI Agent solution that automates various business tasks and processes using intelligent agents. These agents can handle customer interactions, data analysis, workflow management, and more, thereby enhancing productivity and reducing manual intervention. With a focus on adaptability and integration, AgentsForce enables organizations to optimize operations seamlessly across multiple platforms.

AutoAct is designed to streamline the development of intelligent agents by combining LLM-driven reasoning with structured planning and modular tool integration. It offers a Planner component to generate action sequences, a ToolKit for defining and invoking external APIs, and a Memory module to maintain context. With logging, error handling, and configurable policies, AutoAct supports robust end-to-end automation for tasks such as data analysis, content generation, and interactive assistants. Developers can customize workflows, extend tools, and deploy agents on-premise or in the cloud.

IOTA ERP and CRM systems specialize in various sectors, including finance, logistics, retail, and manufacturing. Offering functional, fast, and convenient solutions, they enhance business efficiency and streamline operations. The systems are accessible via mobile devices and are fully responsive. We utilize a robust tech stack, including Golang and HTMX, to handle massive data processing and ensure scalable solutions. Embracing AI/ML technologies, we integrate advanced solutions like large language models into business processes to increase productivity. Additionally, IOTA ERP systems can be deployed both on-premises and in the cloud, providing flexible options to meet diverse business needs.

MASChat provides a flexible framework for orchestrating conversations among multiple AI agents powered by language models. Developers can define agents with specific roles—such as researcher, summarizer, or critic—and specify their prompts, permissions, and communication protocols. MASChat’s central manager handles message routing, ensures context preservation, and logs interactions for traceability. By coordinating specialized agents, MASChat decomposes complex tasks—like research, content creation, or data analysis—into parallel workflows, improving efficiency and insight. It integrates with OpenAI’s GPT APIs or local LLMs and allows plugin extensions for custom behaviors. MASChat is ideal for prototyping multi-agent strategies, simulating collaborative environments, and exploring emergent behaviors in AI systems.

Multi-Agent Systems is designed to simplify the creation, configuration, and execution of distributed agent-based architectures. Developers can define agent behaviors, communication ontologies, and service descriptions within Java classes. The framework handles container setup, message transport, and life-cycle management for agents. Built on standard FIPA protocols, it supports peer-to-peer negotiation, collaborative planning, and modular extension. Users can run, monitor, and debug multi-agent scenarios on a single machine or across networked hosts, making it ideal for research, education, and small-scale deployments.

Nemesys Labs specializes in deploying sophisticated AI-driven solutions across multiple sectors. Our products are designed to seamlessly integrate with existing systems, providing enhanced data analytics, automation, and decision-making capabilities. We focus on creating scalable and customizable AI applications that address key challenges within industries such as healthcare, finance, manufacturing, and more. By leveraging cutting-edge AI technologies, we enable businesses to achieve significant improvements in performance and operational efficiency, ultimately driving growth and innovation.

The Agent Communication Protocol (ACP) is a formal framework designed to enable seamless interaction among autonomous AI agents. ACP specifies a set of message types, headers, and payload conventions, along with agent discovery and registry mechanisms. It supports conversation tracking, version negotiation, and standardized error reporting. By providing language-agnostic JSON schemas and transport-agnostic bindings, ACP reduces integration complexity and allows developers to compose scalable, interoperable multi-agent systems for use in customer service bots, robotic swarms, IoT orchestration, and collaborative AI workflows.

Agent Forge provides a modular architecture for defining, executing, and coordinating AI agents. It offers built-in task orchestration APIs to sequence and parallelize operations, memory modules for long-term context retention, and a plugin system to integrate external services (e.g., LLMs, databases, third-party APIs). Developers can rapidly prototype, test, and deploy agents in production, weaving together complex workflows without managing low-level infrastructure.

Agent-FLAN is designed to simplify the creation of sophisticated AI agent-driven applications by segmenting tasks into planning and execution roles. Users define agent behaviors and workflows via configuration files, specifying input formats, tool interfaces, and communication protocols. The planning agent generates high-level task plans, while execution agents carry out specific actions, such as calling APIs, processing data, or generating content with large language models. Agent-FLAN’s modular architecture supports plug-and-play tool adapters, custom prompt templates, and real-time monitoring dashboards. It seamlessly integrates with popular LLM providers like OpenAI, Anthropic, and Hugging Face, enabling developers to quickly prototype, test, and deploy multi-agent workflows for scenarios such as automated research assistants, dynamic content generation pipelines, and enterprise process automation.