Awesome AI Agents › Collaborative Swarm Systems
OpenDeRisk is an AI-native risk intelligence system designed to provide comprehensive and continuous protection for application systems around the clock. It functions as an intelligent risk manager that leverages advanced AI technologies to perform in-depth root cause analysis (RCA) and diagnostics. The system is built on a multi-agent architecture, where different specialized agents such as SRE-Agent, Code-Agent, ReportAgent, Vis-Agent, and Data-Agent collaborate to analyze logs, traces, and code to quickly identify the root causes of issues. This collaboration enables a dynamic and thorough diagnostic process. One of the standout features of OpenDeRisk is its visualized evidence chain, which fully visualizes the diagnostic process and the evidence supporting the findings. This visualization helps users clearly understand the diagnosis and quickly judge its accuracy. The system is open-source and designed with an open architecture, allowing developers to use its frameworks and code in their own open-source projects. The technical implementation involves a data layer that pulls and processes a large-scale dataset called OpenRCA, which is about 26GB in size. The logic layer uses the multi-agent system to perform deep research RCA, and the visualization layer dynamically renders the entire process and evidence chain. The system also includes digital employees (agents) that work together to handle complex operational diagnostic tasks. OpenDeRisk supports easy installation and setup, with detailed instructions for installing necessary packages, configuring API keys, and running the system locally. It also provides a web interface for users to interact with the system and view diagnostic results. The project acknowledges several related open-source projects and aims to build a community around AI-native risk intelligence systems to improve service quality and foster collaboration among developers. Keywords: AI-native, risk intelligence, root cause analysis, multi-agent system, visualization, open-source, OpenRCA dataset, diagnostic system, application protection, collaboration, digital agents, evidence chain, operational diagnostics, system monitoring, deep research RCA.
https://github.com/derisk-ai/OpenDerisk
AgentVerse is a versatile open-source framework that enables the deployment and collaboration of multiple LLM-based agents for task-solving and simulation applications, supporting research and development in multi-agent AI systems.
Solace Agent Mesh is an open-source event-driven framework for building and orchestrating scalable multi-agent AI systems that integrate with real-world data and systems.
Langroid is a Python framework that enables building LLM-powered applications using a multi-agent programming approach for collaborative problem solving and enhanced developer experience.
EvoAgentX is an automated framework for building a self-evolving ecosystem of AI agents that generate, evaluate, and execute multi-agent workflows based on natural language goals.
agentUniverse is a multi-agent framework based on large language models that enables developers to build collaborative intelligent agents integrating domain expertise for solving complex problems.
Public research log of Hyperspace, a libp2p peer-to-peer network where autonomous agents run experiments across five domains, gossip findings, pool machines into private pods and train models collaboratively.
GPTeam is an open-source multi-agent simulation platform that uses GPT-4 to enable AI agents to collaborate and communicate effectively to achieve predefined goals.
uAgents is a lightweight Python framework by Fetch.ai for creating secure, decentralized autonomous AI agents that operate within a blockchain-enabled network.