superagent-cli 2.8.0

AI Agent self-organizing teams, task allocation, and collaborative CLI tool. 49 commands, 16 integrated open-source projects, 178 role templates.

SuperAgent

AI Agent self-organizing teams, task allocation, and collaborative CLI tool.

One command → agents form teams, split tasks, coordinate work, deliver results.

Highlights

• 49 CLI commands covering the full agent lifecycle
• 16 open-source projects integrated (577k+ total GitHub stars)
• 178 professional agent roles across 14 departments
• 4 execution engines: DeerFlow, Aider, Browser-use, GPT-Researcher
• Zero-cost offline mode: Ollama / LocalAI / llama.cpp
• Pixel-art dashboard: Real-time agent visualization

Quick Start

pip install superagent-cli
superagent auto "Build a todo app with auth" --command builtin

Core Commands

Command	Description
superagent auto "goal"	One sentence → full team automation
superagent auto "goal" --command local	Zero-cost offline execution
superagent role match "task"	Smart role matching from 178 templates
superagent triage route "task"	Intelligent routing to best agent
superagent engine list	Show available execution engines
superagent pipeline show sdlc	View SOP workflow
superagent dashboard serve --team X	Pixel-art visualization
superagent trends search "topic"	Multi-platform trend search
superagent browser run "task"	Web automation
superagent research run "query"	Deep research

Integrated Projects (577k+ Stars)

Project	Stars	Capability
Browser-use	86k	Web automation
agency-agents	76k	178 role templates
DeerFlow	60k	LLM execution engine
Mem0	52k	Semantic memory
Firecrawl	91k	Web scraping
RAGFlow	75k	Document RAG
Aider	25k	Coding agent
GPT-Researcher	18k	Deep research
Composio	12k	200+ service integrations
E2B	7k	Sandbox execution
Star-Office-UI	7k	Pixel-art dashboard
ClawTeam	5k	Team coordination base
LocalAI support	45k	Zero-cost local models
Langfuse	OSS	Execution tracing
Hermes Agent	47k	Learning patterns (design)
ClawTeam-OpenClaw	1k	Enhanced features

Architecture

User → superagent auto "goal"
  → Orchestrator (category detect + role match)
  → Execution Engine (DeerFlow / Aider / Local)
  → Multi-Agent (each in Git Worktree + tmux)
  → File Output + Dashboard Visualization

Installation

pip install superagent-cli          # Core
pip install superagent-cli[all]      # Everything

Install from Source (development)

git clone https://github.com/superagent-cli/superagent.git
cd superagent
pip install -e .           # Core
pip install -e ".[dashboard]"  # + Dashboard

Optional: Local Model (zero cost)

brew install ollama && ollama serve &
ollama pull llama3.2
superagent local register
superagent auto "Build X" --command local

Configuration

# LLM Provider (pick one)
superagent llm add --name deepseek --api-key $DEEPSEEK_API_KEY --base-url https://api.deepseek.com/v1 --model deepseek-chat
superagent llm default deepseek

# Or use local models (free)
superagent local setup --model llama3.2

Documentation

• Usage Guide — Complete 10-section tutorial
• Evaluation Report — 5W2H1R + SWOT analysis

License

MIT