
Autoblocks
LLM Orchestration
LLM evaluation platform for measuring, debugging, and improving AI application reliability.

LLM Orchestration
LLM evaluation platform for measuring, debugging, and improving AI application reliability.
LLM Orchestration
LLM observability and evaluation platform for building production-grade AI applications with tracing, monitoring, and annotation tools.

LLM Orchestration
Smart LLM router that automatically selects the optimal model for each prompt based on quality and cost.
PriceUsage-based

LLM Orchestration
AI model router that automatically selects the best LLM for each query based on cost, latency, and quality optimization.

LLM Orchestration
Pipecat is an open-source framework for building real-time voice and multimodal AI agents with transport, pipeline, and interaction primitives.
LLM Orchestration
Platform for building and deploying AI agents with managed hosting, tool integration, and conversation memory.
LLM Orchestration
LLM orchestration platform for routing prompts to optimal models based on cost, latency, and quality.
LLM Orchestration
Open-source embeddings database for semantic search, LLM orchestration, and language model workflows.

LLM Orchestration
LLM orchestration library for building production AI applications with Python decorators.

LLM Orchestration
Python toolkit for building LLM applications with clean abstractions for prompts, calls, and structured extraction.