# Open source AI agent frameworks: which one fits your job > The right open source AI agent framework depends on the job. This guide sorts LangGraph, CrewAI, AutoGen, OpenHands, and open source Kortix by what each one runs, where memory and state live, and who reviews a change before it lands. URL: https://opensourceaiagentframework.com/best-open-source-ai-agent-framework ## Open source AI agent frameworks at a glance What each framework runs, where state lives, and how work is reviewed. | | Kortix (recommended) | LangGraph | CrewAI | AutoGen | OpenHands | | --- | --- | --- | --- | --- | --- | | What it is | The open-source AI Operating System a company runs and owns. | A low-level orchestration framework for long-running, stateful agents. | A Python framework for role-based agent teams and event-driven flows. | A programming framework for multi-agent systems your app hosts. | A self-hosted front end that runs coding agents. | | Open source | Yes | Yes | Yes | Yes | Yes | | What you own | The whole system: agents, skills, memory, and connectors in your repo. | Your application code; the framework's runtime stays in it. | Your Python app and the crew and flow definitions. | Your app and the agent team you compose. | The self-hosted stack you run on your own machine. | | Runs the agents or only defines them | Runs them: each session on its own cloud computer. | Defines and runs orchestration inside your own application. | Defines and runs crews inside your Python application. | Defines and runs teams your application hosts. | Runs coding agents on a machine or server you pick. | | Where memory and state live | In the repo as files, versioned in the same git history. | In the framework's persistence layer, wired into your app. | In CrewAI's memory store, with scopes and vector recall. | In your app, saved to disk and loaded from storage. | In each conversation's workspace and persisted state on the host. | | Model choice | Any model with your own keys, or a ChatGPT subscription. | Any model; docs cover OpenAI, Anthropic, Google. | Any model you wire in; tools reach any API. | Model clients you add, including OpenAI and others. | Bring your own model: use with any LLM. | | Human review of changes | Work reaches main through a change request a person reviews. | Human-in-the-loop: inspect and edit state at a chosen point. | An optional human_input field pauses a task for a person. | A UserProxyAgent pauses the team for approval or feedback. | You review the conversation and the changes in your repo. | | The job it fits | Running company work end to end, owned and reviewed. | Custom stateful runtimes embedded in your own application. | Role-based agent teams inside a Python application. | Research and multi-agent systems your application hosts. | Coding tasks: an agent that develops in your repositories. | ## The company as files in one repo `acme-co/` ``` acme-co/ your whole company, as files agents/ who does the work skills/ how your company does a job memory/ what it has learned so far kortix.yaml rules, triggers, connectors, machine ``` Source: https://kortix.com Agents, skills, memory, and configuration are files you can read and diff. ## Which open source AI agent framework fits your job Start with the shape of the work, then pick. A single agent loop inside a service you control points to a low-level orchestration framework such as LangGraph. A team of named roles that runs in Python points to CrewAI. Research into multi-agent behavior that you host yourself points to AutoGen. Coding work in your repositories points to OpenHands. Company work that must land as reviewed changes your team owns points to Kortix, which runs each session on its own cloud computer and returns finished work through a change request. The comparison table on this page sets the five side by side. ## What the question really depends on Most comparisons rank frameworks on features and skip the layer each one sits in. A framework defines agents: prompts, tools, and control flow live in your application, and your team owns the runtime around them. A platform runs agents and holds the company state they work from. Two questions decide the layer. Where does the finished work land, and can you read the history of how it got there? If the answer is inside your application and your own logs, a framework is the right layer. If the answer is a repo your team owns, with every change reviewed before it merges, you are choosing a platform. The [open source agent framework alternatives](/open-source-agent-framework-alternatives) guide sets the frameworks side by side, and [framework or platform](/framework-or-platform) explains the split. ## A framework defines agents; a platform runs the work LangGraph, CrewAI, and AutoGen define and run agents inside an application you build and operate. That is the right layer when the agent is part of your product. When the agent is part of the company, the layer changes. Kortix is the open-source AI Operating System: agents, skills, company memory, and connectors live in one git repo you own, each session runs on its own cloud computer, and session work reaches main through a change request a person reviews. Merge is default-deny for agents. To see the two layers on one stack, read [Kortix versus LangGraph](/kortix-vs-langgraph). ## Open source AI agent frameworks, answered ### What is the difference between an AI agent framework and a platform? A framework defines agents inside an application your team builds and runs. A platform runs the agents and holds the state they work from. Kortix is the open-source platform: it runs each session on its own cloud computer and lands work as reviewed changes. ### Do I need a framework if I use Kortix? No. Kortix runs agents, skills, memory, and connectors from one git repo you own. You would add a framework only when a specific agent has to live inside your own application. ### Which open source AI agent framework should a small team start with? Match the framework to the job. LangGraph for a custom stateful loop, CrewAI for role-based teams in Python, AutoGen for multi-agent research, OpenHands for coding work. Choose Kortix when the work has to be owned and reviewed. ### Is Kortix open source? Yes. Kortix is open source. Read it, fork it, audit it, and run it on Kortix Cloud, in your VPC, or on your own on-prem network. ## Own the layer your agents run on One repo for the agents, the skills, the memory, and the connectors. [Try Kortix](https://kortix.com)