Agents

Active
GitHub Python MIT

Description

Intelligent automation and multi-agent orchestration for Claude Code. Supports automated workflows, task coordination, and intelligent agent system building.

Key Features

  • 84 composable plugins — Each plugin is isolated and composable, loading only its agents, commands, and skills into context
  • 192 domain-expert agents — Covering architecture, languages, infrastructure, security, data, ML, docs, business, and SEO
  • Five-harness native support — Single Markdown source generates native artifacts for Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, Copilot
  • 102 slash commands — Scaffolding, security scans, test generation, infrastructure setup and more
  • 16 multi-agent orchestrators — Full-stack, security, ML, incident response multi-agent workflow orchestration
  • Three-tier model strategy — Opus 4.7 (architecture/security), inherit (user choice), Sonnet (docs/tests), Haiku (fast ops)

Use Cases

💡 Full-stack project bootstrapping — One-click Django/FastAPI scaffolding via python-development plugin with tests, CI/CD, and security checks
💡 Automated security auditing — 192 agents in security plugin scan code vulnerabilities, dependency chain risks, and configuration issues
💡 Multi-language code migration — Language-specific expert agents assist cross-language refactoring with domain-tailored skill sets
💡 AI-assisted documentation — Auto-maintain API docs, architecture diagrams, and CHANGELOG via docs plugins
💡 Cross-IDE unified experience — Same plugins provide consistent agent capabilities across Claude Code, Cursor, Codex CLI and more

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (39.4k stars)
  • Permissive open-source license (MIT)
  • Responsive to issues, low backlog

Quick Start

```bash
# Claude Code
git clone https://github.com/wshobson/agents.git ~/agents
cd ~/agents
/plugin marketplace add wshobson/agents
/plugin install python-development

# Codex CLI
npx codex-marketplace add wshobson/agents

# Gemini CLI
make generate HARNESS=gemini && gemini extensions install .
```

Related Projects

LazyLLM

3.9k · Python
Active A+

LazyLLM is a lightweight multi-agent LLM application framework offering the easiest way to build multi-agent LLM apps, with built-in RAG, knowledge graph, fine-tuning, and integration with LangChain and LlamaIndex ecosystems.

multi-agentframeworkrag +3
  • · Low-code multi-agent application assembly with built-in data flow and functional modules like Lego blocks
  • · One-click deployment with lightweight gateway for POC and Kubernetes packaging for production
  • · Cross-platform compatibility across bare-metal, Slurm clusters, and public clouds without code changes

Ouroboros

5.8k · Python
Active A

Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.

multi-agentframeworkagent +4
  • · Spec-first workflow: Socratic interview → immutable seed spec → execution → evaluation
  • · Multi-runtime adapter supporting Claude Code, Codex CLI, OpenCode, Hermes, Gemini, Kiro, Copilot
  • · Three-layer architecture: Kernel (contract engine), Plugins (domain workflows), Shell (TUI cockpit)

DeepResearchAgent

3.5k · Python
Stale B

DeepResearchAgent is a hierarchical multi-agent system designed for deep research tasks and general-purpose problem solving, using a top-level planning agent to coordinate specialized sub-agents for automated task decomposition and efficient cross-domain execution.

multi-agentframeworkpython +3
  • · Hierarchical multi-agent system with top-level planning agent coordinating specialized sub-agents
  • · RSPL protocol layer modeling prompts, agents, tools, environments, and memory as versioned resources
  • · SEPL self-evolution protocol for proposing, assessing, and committing improvements with rollback support

Oh My ClaudeCode

39.0k · TypeScript
Active A+

Teams-first multi-agent orchestration for Claude Code. Designed for team collaboration with support for multi-agent coordination, task distribution, and result integration to enhance team AI development efficiency.

multi-agentclaude-codeteam-collaboration +2
  • · Multi-agent team orchestration — /team command launches parallel multi-agent collaboration with tmux workers
  • · Autopilot mode — Describe goals in natural language for automatic decomposition, execution, and verification
  • · Deep interview — Socratic questioning to clarify requirements and expose hidden assumptions before execution