“monitoring”

Open-source agent harness from LangChain for building agents with code, with LangSmith for testing and monitoring.

PHP framework for agentic applications with workflows, human-in-the-loop, MCP connectors, RAG and multi-provider LLM support.

Python framework and runtime for building agents, serving them over a REST API and MCP server, and managing them from a web control plane.

JavaScript and TypeScript framework of interoperable components for building LLM apps and agents, with LangGraph.js and Deep Agents above it.

Open-source Python framework from deepset for modular pipelines and agent workflows covering retrieval, tool use and generation.

Python SDK for tracing agents and scoring their traces with prompt-based judges, to find failures in production.