Features
Agent loop with Thought/Action/Observation cycle
LLM-controlled decision making
Pluggable tool interface (Python class)
Python REPL tool for executing code
Google Search tool via SerpAPI
Customizable prompt template
Date injection in prompt to avoid future-date confusion
Stop token trick to prevent hallucinated tool use
Minimal codebase for easy understanding
Simple parsing of Action and Action Input
Iterative reasoning until final answer
Tool name and description for LLM guidance
Built from scratch in under 200 lines of code
Role-based agent assignment (PM, architect, engineer, QA)
Structured output generation (requirements, design, code)
Data Interpreter for data analysis tasks
SELA module for self-evolving agents
Multi-agent collaboration and workflow orchestration
Meta-programming support for custom agent behaviors
Modular and extensible architecture
Built-in demo projects and case studies
MIT License fully open-source
Flow orchestration for complex agent pipelines
Integration with GitHub Actions and CI/CD
Community-driven with GitHub and Discord
