LangGraph
langchain-ai.github.io/langgraph
A low-level framework from LangChain for building stateful, multi-agent AI applications as explicit graphs, with controllable execution flow, human-in-the-loop support, and built-in persistence.
Why it is useful
Solves the control problem with LLM agents — instead of hoping the agent reasons correctly through a chain, you define the possible states and transitions explicitly as a graph. This makes agent behavior predictable, debuggable, and resumable across sessions. The human-in-the-loop support lets you pause execution at any node for approval before continuing, which is essential for production agentic workflows.
More in Developer Utilities
Other developer utilities you might not have heard of.
- Agent Skills HubFind security-reviewed MCP servers and AI agent skills with install guidance, permission notes, repo signals, and safer Claude Code team workflow routes.
- MXToolboxA suite of free network diagnostic tools focused on email infrastructure — MX record lookup, SPF/DKIM/DMARC testing, blacklist checking, and SMTP diagnostics.
- MedusaOpen-source, headless commerce framework — build a fully custom online store backend as a free, self-hostable alternative to Shopify.
- RAGFlowAn open-source RAG engine with deep document understanding — extracts structured content from PDFs, presentations, spreadsheets, and images using OCR and layout analysis before chunking.
- RailwayDeploy a database, backend, or full app straight from a GitHub repo with almost no configuration — Postgres, Redis, Node, Python, and more.
- UnslothA fine-tuning library that makes QLoRA and LoRA training 2x faster and use 50% less memory than standard implementations, enabling fine-tuning of large models on consumer GPUs.