Features
Open-source LLM for generating API calls
Supports parallel and multiple function calls
Multi-language: Python, Java, JavaScript, REST
Berkeley Function Calling Leaderboard (BFCL)
GoEX runtime for safe action execution
GoEX undo and damage confinement abstractions
Retriever-Aware FineTuning (RAFT) for RAG
OpenFunctions v2 model on HuggingFace
Gorilla CLI for command-line tool calling
Gorilla Spotlight Search integration
Apache 2.0 license for commercial use
No sign-up required via Colab notebook
State-of-the-art performance on par with GPT-4
@ai_fn decorator for LLM-powered Python functions
@ai_classifier decorator for text classification
Structured data extraction via Pydantic models
Agent loops with tool calling and function calling
Built-in streaming (SSE) support
Async-first API for concurrent applications
Rate limiting and automatic retries
LLM response caching for performance
Concurrency control for workload management
CLI tool for monitoring and debugging
SQLite state store for persistence
OpenAI and Anthropic model support
Embeddings generation for semantic search
Local execution with no cloud dependency
Self-hosted deployable as a library
