Features
Multi-language SDK: JS/TS, Go, Python, Dart
Unified generation API with streaming and tool calling
Plugin integration for Gemini, OpenAI, Anthropic, xAI, DeepSeek, Ollama
Middleware system for retries, fallback, tool approval
Dotprompt templating and management (TS, Dart 0.14.0+)
Local Developer UI for debugging and tuning prompts
Gemini Nano on-device inference
Image generation and multimodal output
Agentic app scaffolding with built-in tool use
Open-source, Apache 2.0 licensed
Type-safe API with TypeScript and Go
Compatible with Firebase and Google Cloud services
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
