The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Swarms is a Python framework for building and running coordinated networks of AI agents, installable via pip or uv and configured through environment variables including an Anthropic API key for Claude access. It connects to Claude through the Anthropic API, treating Claude models as interchangeable LLM backends alongside OpenAI, Groq, and others. The core building block is the Agent class, which pairs an LLM with tools and memory and supports an auto loop mode where the agent continues reasoning and acting until it self-determines task completion, rather than stopping after a fixed iteration count. Beyond single agents, the framework provides prebuilt multi-agent architectures including sequential, concurrent, and hierarchical swarms, and supports interoperability with MCP and the x402 protocol. A companion marketplace at swarms.world lets users share and discover agent configurations. The framework targets developers and engineering teams building production pipelines for complex, multi-step tasks such as research, iterative writing, and analysis workflows that benefit from coordinated agent collaboration.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/kyegomez/swarms && cp swarms/*.md ~/.claude/agents/4 items in this repository
Perform comprehensive code reviews focusing on best practices, security vulnerabilities, performance optimization, and maintainability
Create effective data visualizations using best practices for clarity, accuracy, and visual communication of insights
Perform comprehensive financial analysis including DCF modeling, ratio analysis, and financial statement evaluation for companies and investment opportunities
Build agents and multi-agent systems with the Swarms framework — the Agent class, tools, autonomous loops, memory, and the 15+ multi-agent architectures (SequentialWorkflow, ConcurrentWorkflow, GraphWorkflow, HierarchicalSwarm, SwarmRouter, and more). Use whenever writing, reviewing, or debugging code that imports `swarms`.
Subagents overview
What people ask about swarms
What is kyegomez/swarms?
+
kyegomez/swarms is subagents for the Claude AI ecosystem. The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai It has 7.1k GitHub stars and its last recorded update is dated 2026-09-03.
How do I install swarms?
+
You can install swarms by cloning the repository (https://github.com/kyegomez/swarms) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is kyegomez/swarms safe to use?
+
Our security agent has analyzed kyegomez/swarms and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains kyegomez/swarms?
+
kyegomez/swarms is maintained by kyegomez. The last recorded GitHub activity is dated 2026-09-03, with 166 open issues.
Are there alternatives to swarms?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy swarms to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/kyegomez-swarms)<a href="https://claudewave.com/repo/kyegomez-swarms"><img src="https://claudewave.com/api/badge/kyegomez-swarms" alt="Featured on ClaudeWave: kyegomez/swarms" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.