Features
AI agent that works inside game engines
Executes actions and makes real changes to projects
Sub-1 GB LLM for on-device inference
Emotional tuning for NPCs
Retrieval-Augmented Generation for NPCs
Dynamic AI NPCs and companions
Rapid prototyping from ideas to playable worlds
On-device AI without cloud dependency
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
