Features
Fable5-structured reasoning pipeline
Automated query decomposition
Benchmark suite for quality-cost tradeoff measurement
Cost-optimization modeling per task type (COST.md)
Custom hooks for preprocessing and validation
Output style templates for consistent formatting
Routing guides for code vs. writing tasks
Blind-test parity validation scripts
Self-hosted operational model (no external API dependency)
AGPL-3.0 open-source license
Plugin system for Claude Code
Skill-based session mode (SKILL.md trigger)
Markdown-based configuration
Voice/voice conversation: not supported
@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
