openJiuwen-ai/jiuwenswarm

JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your fingertips through various communication apps you use daily.

What it solves

JiuwenSwarm automates complex, multi-step tasks by coordinating teams of AI agents. It bridges the gap between high-level user intent and execution, allowing specialized agents to collaborate, negotiate, and perform tasks that are too intricate for a single AI model to handle alone.

How it works

The system uses a "Leader" agent that breaks down your request into smaller, manageable tasks. It then assigns these tasks to specialized "teammate" agents. These agents can operate on a single machine or be distributed across a cluster. The system supports "Swarmflow," a way to define deterministic, multi-stage workflows using Python, and includes features like human-in-the-loop approval, skill self-evolution based on error signals, and a centralized hub for sharing and reusing agent capabilities.

Who it’s for

It is designed for developers and teams who need to automate complex workflows and want a flexible, scalable agent system. It is suitable for those who need to integrate AI agents into their existing chat apps (like Slack, Discord, or WeChat), terminal environments, or web interfaces.

Highlights

  • Multi-agent orchestration with a Leader-Teammate structure for complex task decomposition.
  • Distributed deployment support across processes and machines.
  • Skill self-evolution that automatically optimizes agent capabilities based on performance and user feedback.
  • Secure execution with mandatory tool approval, file access whitelisting, and interception of sensitive operations.
  • Broad compatibility with major AI model providers, including OpenAI-compatible APIs and local models.
  • Extensible via the Swarm Skills Hub for sharing and remixing agent capabilities.

Related

  • Project
    kyegomez/swarms

    An enterprise-grade multi-agent orchestration framework that provides pre-built architectures for coordinating multiple AI agents in sequential, concurrent, and hierarchical workflows.

  • Project
    VRSEN/agency-swarm

    A framework for building multi-agent AI applications that organizes agent collaboration using real-world organizational structures and directional communication flows.

  • Project
    HKUDS/AutoSwarm

    AutoSwarm is a Python framework that automatically builds, runs, and learns from a swarm of AI agents organized as a virtual company. It offers a CLI and a visual Office UI, supports adaptive team creation, Kanban‑driven orchestration, and experience‑based playbook generation, and integrates with external LLM back‑ends like JiuwenSwarm.

  • Project
    desplega-ai/agent-swarm

    An open-source AI operating system that coordinates a lead agent and Docker-isolated worker agents to automate complex workflows across Slack, GitHub, and email.

  • Project
    VRSEN/OpenSwarm

    A multi-agent system that coordinates specialized AI agents to generate professional deliverables like slide decks, research reports, and videos from a single terminal prompt.