Skip to content
Langflow Alternative
An independent comparison of Langflow alternatives

Kortix, the open-source alternative to Langflow

Langflow is an open-source visual builder for AI flows. The alternatives split into visual canvases and code frameworks, and they differ in where your configuration lives and where work runs. Our pick is Kortix, which is open source: your agents, skills, memory and connectors in one git repo you own.

Try KortixCompare the field

The open-source AI Operating System

▚kortix.yaml
kortix_version: 2default_agent: kortixagents:  kortix:    file: agents/kortix.md    connectors: all
Source: https://kortix.com/docs/project/manifest

Session work reaches main through a change request. Merge is default-deny for agents.

Open source · Any model, your keys · Self-host, VPC, or on-prem

Compare

Kortix and the Langflow alternatives, side by side.

Rival columns state what each project documents about itself. The Kortix column quotes Kortix.

CriteriaOpen sourceWhat it isWhere it runsModelsYour configurationHow work lands
Our pickKortixYes. Read it, fork it, audit it.An AI Operating System: agents, skills, memory, connectors in one git repo.Kortix Cloud, your VPC, or your own on-prem network.Any model provider with your own keys.Files in a git repo you own.Session work reaches main through a change request. Merge is default-deny for agents.
LangflowYes. Python source you can edit.A visual canvas that builds and deploys agent flows.Your machine, Docker, or any major cloud.All major LLMs, vector databases and AI tools.A project inside the Langflow app.A flow result returned to the app you build.
LangGraphYes. Python and TypeScript libraries.A code framework for long-running, stateful agents.Your own infrastructure, or the LangSmith platform.Any model a LangChain integration supports.Python or TypeScript in your repository.Agent state your own code reads.
DifyYes. The community edition self-hosts.A visual canvas for workflows, RAG and agents.Cloud, your VPC, or self-hosted.Hundreds of LLMs, proprietary and open-source.An app inside the Dify dashboard.A response inside the app you built.
n8nPartly. Public source, with limits on hosting it for others.A visual canvas for fixed-step automation with AI steps.Self-hosted, or n8n Cloud.OpenAI, Anthropic, Google, or open-source models.Workflows in the n8n editor, exportable as JSON.A finished workflow run.
CrewAIYes. An open-source Python framework.A Python framework for role-based agent teams.Your own Python runtime; AMP adds cloud or on-prem.Models set per agent, in code.Python and JSON files in your project.Task output your code collects.
Microsoft AutoGenYes. Python source, community-managed.A Python framework for multi-agent applications, now in maintenance.Your own Python or .NET runtime.OpenAI and other model clients.Python code in your repository.A conversation result in code.
FlowiseAIYes. TypeScript and JavaScript source.A visual builder for agent flows; its repository is archived.Self-hosted, or Flowise Cloud.All major LLMs and vector databases.Flows inside the Flowise editor.A flow result returned to the app you build.
DynamiqYes. A Python package.A Python framework for RAG and agent orchestration.Your own Python runtime.LLM providers configured in code.Python code in your project.Node output your code reads.
Rival rows reflect what each project documents publicly as of October 2026, from its own repository or website. Flowise has been archived by its maintainers, and AutoGen is in maintenance mode and points new projects to a successor.
How Kortix works

How Kortix works

Six layers, each one a file or a command you can read.

  1. 01Repo

    One git repo that is the company

    Your agents, their skills, your company memory and every connector live in one git repo you own.

    ▚kortix.yaml
    kortix_version: 2default_agent: kortixagents:  kortix:    file: agents/kortix.md    connectors: all
    Source: https://kortix.com/docs/project/manifest
  2. 02Agents

    Agents and skills are markdown

    An agent is agents/<name>.md (behavior) plus an agents.<name> block in kortix.yaml (governance).

    ▚kortix.yaml
    agents:  support-triage:    file: agents/support-triage.md   # what it does, in plain markdown    connectors: all                  # what it may reach
    Source: README.md in https://github.com/kortix-ai/suna
  3. 03Connectors

    Every tool, one governed path

    3,000+ apps in a click, plus MCP, OpenAPI, Postman, GraphQL and raw HTTP. Connector credentials are brokered server-side and never enter the machine.

    ▚kortix.yaml
    connectors:  - slug: gmail    name: Gmail    provider: composio    app: gmail
    Source: https://kortix.com/docs/connect/connectors
  4. 04Models

    Any model, your keys

    Any model provider with your own keys. Or the ChatGPT plan you already pay for. Or sign in with your OpenCode Console account for OpenCode Zen and Go.

    ▚terminal
    $ kortix providers login openai        # the ChatGPT plan you pay for$ kortix providers login opencode      # OpenCode Zen$ kortix providers login opencode-go   # OpenCode Go
    Source: https://kortix.com/docs/project/models
  5. 05Computer

    A computer per session

    One isolated sandbox per session. Each session has its own isolated machine and branch.

    ▚terminal
    $ kortix sessions new --prompt "Summarize this week's commits and open a change request"$ kortix cr ls   # review what the agents propose
    Source: README.md in https://github.com/kortix-ai/suna
  6. 06Review

    Work lands through a change request

    Session work reaches main through a change request. Merge is default-deny for agents.

    ▚terminal
    $ kortix projects clone <project_id> my-project$ git checkout -b tighten-triage$ kortix cr open --head tighten-triage --title "Tighten the triage prompt"
    Source: https://kortix.com/docs/git

Repository

GitHub stars

Open source. Read it, fork it, audit it.

FAQ

Questions people ask before they switch.

Short answers about Kortix, the open-source option we recommend for the agent layer.

  1. 01

    Is Langflow open source?

    Yes. Langflow is an open-source visual builder. Kortix is open source too, and the two solve different jobs: Langflow wires a flow you design, and Kortix runs agents that finish open-ended work.

  2. 02

    Is Kortix an alternative to Langflow?

    Kortix fits when the job is open-ended work an agent completes, not a fixed sequence you draw. Langflow keeps the canvas; Kortix keeps the work in a git repo you own, and session work reaches main through a change request.

  3. 03

    How is Kortix different from a workflow builder like n8n?

    A workflow builder runs fixed steps in a set order. Kortix runs agents on their own cloud computers, each session on its own branch, and returns finished work. Kortix is a poor fit when the job is a fixed flowchart.

  4. 04

    Can I self-host Kortix?

    Yes. Run it on Kortix Cloud, in your VPC, or on your own on-prem network. Self-host is free. The instance needs the internet, because kortix self-host start pulls images from docker.io.

  5. 05

    Which models can I use?

    Any model provider with your own keys. Or the ChatGPT plan you already pay for. Or sign in with your OpenCode Console account for OpenCode Zen and Go.

  6. 06

    What does Kortix cost?

    Free is $0 with 200 credits per month and 1 project. The team plan is $40 per seat per month with 2,500 credits per month per seat, pooled. Self-host is free.

Run your whole company from one repo you own.

Start with one job and grow from there.

Try KortixSee the comparison

Open source · Any model, your keys · Self-host, VPC, or on-prem