Glossary

LangGraph

What is LangGraph?

LangGraph is an open-source framework from the LangChain ecosystem for modelling AI agents and multi-step processes as a graph of nodes and edges. A shared state is passed from step to step, and loops, branches, checkpointing and interruptions for human approval are built in. Version 1.0 was released in October 2025. One example is an agent that researches a topic, writes a draft and waits for approval before sending it.

How KI.ordo helps

KI.ordo flows apply a similar idea (steps, branches and sub-flows) without programming.

Learn more →

Topics

Framework
Agents
Workflows

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

LangChain

LangChain is an open-source framework for Python and JavaScript that developers use to build applications based on language models. It provides unified interfaces to many model providers as well as building blocks for tool calling, agents, document processing and retrieval-augmented generation. Since version 1.0 (October 2025), LangChain's agents are built on LangGraph. Typical uses include chatbots that search internal documents and agents that call external services.

Framework
Development
+1

Intelligent Agents

An intelligent agent is a system that perceives its environment, processes information and chooses actions on its own in order to reach a goal. Today the term usually refers to software built on large language models that follows instructions, draws on knowledge and calls tools such as a search function or an API. How much an agent may do independently should be decided deliberately. Example: an agent answers customer questions using the product documentation.

Agents
Autonomy
+1

Crew AI

CrewAI is an open-source Python framework for combining several AI agents into a team (a 'crew'). Each agent is given a role, a goal and suitable tools; tasks are distributed and results passed on. In addition, 'flows' provide tightly controlled, event-driven workflows. For example, a research agent gathers information and a writing agent turns it into a report.

multi-agent
framework
+1

Human-in-the-Loop

Human-in-the-loop describes workflows in which people step into an AI process at defined points: they review results, approve or correct them, or take over difficult cases. The principle reduces the risk of faulty output and keeps accountability with people, especially for decisions affecting individuals, money or legal matters. Example: an AI agent drafts replies to customer enquiries and a member of staff checks them before they are sent.

Approval
Oversight
+1