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 addresses the difficulty of automating complex, multi-stage tasks that require specialized roles and coordination. It provides a system for managing multi-agent collaboration, allowing a "Leader" agent to decompose tasks and assemble specialized teams to deliver end-to-end results from a natural language intent.

How it works

The system operates in two primary modes: Agent mode for independent task handling and Cluster mode for multi-agent collaboration. It utilizes a "Leader" agent to orchestrate specialized teammates who can be deployed across a single machine or a distributed cluster.

Key technical mechanisms include:

  • Swarmflow: Deterministic multi-stage workflows defined via Python scripts with support for Human-in-the-Loop (HITL) and token budget management.
  • Skill Self-Evolution: A feedback loop that detects error signals or user dissatisfaction to automatically optimize skill definitions.
  • Auto Harness: An evaluation-driven system that optimizes the execution harness without requiring model-weight training.
  • Integration: Connects to various LLM providers (Huawei Cloud MaaS, OpenAI, DeepSeek, etc.) and integrates with multiple communication channels like Telegram, Discord, Slack, and WeChat.

Who it’s for

Developers and teams who need to automate complex workflows, build distributed agent swarms, and create reusable AI capabilities (Skills) that can be shared via a central hub.

Highlights

  • Distributed Architecture: Agents can be deployed across multiple processes and machines.
  • Skill Ecosystem: A dedicated Swarm Skills Hub for searching, installing, and publishing reusable capability assets.
  • Multimodal Support: Supports image attachments and multimodal conversations.
  • Flexible Interfaces: Accessible via Web UI, Terminal User Interface (TUI), or integrated chat apps.
  • Security Controls: Includes tool execution approval, file access whitelists, and sensitive operation interception.

Related

  • Project
    kyegomez/swarms

    A production-ready multi-agent orchestration framework that provides pre-built architectures for coordinating multiple AI agents to solve complex tasks.

  • Project
    desplega-ai/agent-swarm

    agent‑swarm is an open‑source platform that turns a lead AI agent into a task‑routing hub, delegating work to containerised worker agents (Claude Code, Codex, etc.). It integrates with Slack, GitHub, email, and many other tools, persisting context via vector memory, and can automatically generate PRs, replies, or scheduled scripts. The system is model‑agnostic, runs via Docker (or Helm on Kubernetes), and is licensed under MIT.

  • Project
    VRSEN/agency-swarm

    A framework for building multi-agent AI applications that organizes agents into collaborative swarms based on real-world organizational structures.

  • 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.

  • Project
    openJiuwen-ai/agent-core

    A high-performance Python SDK and runtime for building LLM agents, featuring both autonomous ReAct agents and structured workflow orchestration with state recovery.