Features
Multi-LLM orchestration (Claude, Gemini, Codex, Ollama, Mistral)
Intelligent routing of tasks to best model
Pipeline/workflow chaining of agents
Autopilot mode for autonomous execution
Multi-agent modes: Compare, Debate, Correction, Consensus
Agentic execution with file editing and bash commands
Persistent memory with vector search
AST indexing and dependency graph analysis
Indexing and search features
TUI commands (/compare, /debate, etc.)
CLI commands (puzldai run, puzldai agent, etc.)
Observation layer for monitoring
Training data generation support
@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
