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...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 53 minutes ago
Added to GitGenius on September 1st, 2026
Created on March 5th, 2026
Open Issues & Pull Requests: 1,296 (-1)
GitHub issues: Enabled
Number of forks: 1,160
Total Stargazers: 7,611 (+8)
Total Subscribers: 458 (+1)

Repository Insights (GitGenius)

Median issue/PR response: 9.9 hours
Mean response time: 3.0 days
90th percentile: 10.9 days
Tracked items: 48

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 10% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 941
New in 7 days: 292
Closed in 7 days: 117
Avg open age: 22 days
Stale 30+ days: 230
Stale 90+ days: 16

Recent activity

Opened in 7 days: 265
Closed in 7 days: 113
Comments in 7 days: 55
Events in 7 days: 818

Top labels

  • sig/jiuwenswarm (2,069)
  • priority/unspecified (1,266)
  • bug (639)
  • priority/major (519)
  • priority/normal (468)
  • feature (177)
  • sig/jiuwenclaw (111)
  • priority/hint (77)

Detailed Description

JiuwenSwarm is an agent system that orchestrates multi-agent collaboration for automating complex tasks through natural language.

The tool addresses the challenge of coordinating multiple AI agents to work together on intricate problems. It works by designating a Leader agent that decomposes tasks and assembles specialized teams, which then negotiate and collaborate dynamically. The system supports both single-machine and distributed deployments across processes and machines. Users interact through natural language to drive multi-agent collaboration, skill invocation, and tool execution, receiving end-to-end results from intent to completion.

Developers should choose this tool if they need to automate workflows requiring coordination between multiple specialized agents rather than a single model. It suits projects where tasks naturally decompose into stages or require human-in-the-loop approval at certain points. The tool distinguishes itself through deterministic multi-stage workflows called Swarmflow, which allow handoffs between stage agents with support for human intervention and token budget constraints. It also includes skill self-evolution, where the system automatically detects errors and user dissatisfaction to optimize skill definitions without model retraining. A Swarm Skills Hub enables building capabilities once and reusing them across deployments. The system provides tool permissions and security controls, requiring approval before tool execution and enforcing file access whitelists.

Development activity shows consistent engagement with the project maintaining active documentation in multiple languages and providing accessible entry points through one-click desktop installation. The tool integrates with multiple AI infrastructure platforms including Huawei Cloud MaaS and OpenAI-compatible APIs, indicating ongoing work to support diverse deployment environments. The presence of a dedicated Swarm Skills Hub and TUI monitoring features for workflow execution demonstrates investment in developer experience and operational visibility.