---
title: "Which Open-Source AI Agent Framework Should Enterprises Use?"
slug: "open-source-ai-agent-framework-enterprise-where-it-runs"
author: "Miguel Amigot"
date: "2026-11-19 12:00:00"
category: "Premium"
sector: "enterprise"
topics: "open-source AI agent framework, enterprise AI agents, LangGraph, CrewAI, Microsoft Agent Framework, OpenAI Agents SDK, Claude Agent SDK, Google ADK, MCP, self-hosted agent platform, agent governance, model-agnostic AI"
summary: "LangGraph, CrewAI, Microsoft Agent Framework, OpenAI Agents SDK, Claude Agent SDK and Google ADK compared from their own repositories: licence, maintainer, latest version, models, and what each leaves to you when agents go to production."
banner: ""
thumbnail: ""
linkedin: |
  "Which open-source agent framework should we use?" is the right question with the wrong scope.

  We checked six frameworks against their own repositories on 18 November 2026. LangGraph, CrewAI, the OpenAI Agents SDK and Microsoft Agent Framework are MIT. Google ADK is Apache 2.0. The Claude Agent SDK ships an MIT licence file, but its use is governed by Anthropic's Commercial Terms.

  All of them are libraries your engineers import. Identity, RBAC, audit logs, multi-tenant hosting and per-agent model choice sit one layer up, and each vendor sells that layer: LangSmith Deployment, CrewAI AMP, Gemini Enterprise Agent Platform. LangSmith's self-hosted control plane requires its Enterprise plan.

  Pick the framework for the code. Then decide who owns the layer the agents run on.

  On ibl.ai you own all the code and the data: the platform layer runs in your cloud, on-premise or air-gapped, on any model, with no per-seat pricing, and it speaks MCP to whatever framework your team picks.

  #iblai #AgenticAI #EnterpriseAI #AIAgents #OpenSource #MCP
faqs:
  - question: "What is the best open-source AI agent framework for enterprises?"
    answer: "There is no single winner. LangGraph (MIT) is a common pick for long-running, stateful workflows; CrewAI (MIT) for role-based multi-agent crews; Microsoft Agent Framework (MIT) for .NET and Python shops; the OpenAI Agents SDK (MIT) for a light, provider-agnostic loop; Google ADK (Apache 2.0) for Google Cloud teams. Choose by language, state model and team skills."
  - question: "Is the Claude Agent SDK open source?"
    answer: "Its repository carries an MIT licence file and the source is public, but its own README says use of the SDK is governed by Anthropic's Commercial Terms of Service. It runs the Claude Code binary as a library, so treat it as a Claude-specific SDK rather than a model-agnostic framework."
  - question: "What does an agent framework leave out for production?"
    answer: "A framework is a library. Single sign-on, role-based access, an audit trail of who changed which agent, multi-tenant hosting, per-agent model choice and a user interface sit in a platform layer. Each framework vendor sells that layer commercially; ibl.ai provides it as a platform you deploy on your own infrastructure."
  - question: "Is ibl.ai open source?"
    answer: "Partly. The application and toolkit repositories (iblai/os, iblai/base, iblai/lms, iblai/infra-cli, iblai/ontology and the .iblai agent standard) are public under MIT. The backend and infrastructure come under a perpetual licence, with full source code transferred in the Codebase Transfer engagement."
---

## The Short Answer

**The open-source AI agent frameworks enterprises shortlist are LangGraph, CrewAI, Microsoft Agent Framework, the OpenAI Agents SDK and Google ADK, all permissively licensed, and LangGraph is a common pick for long-running stateful workflows. A framework is a library, not where agents run: ibl.ai is the platform layer above it, with SSO, RBAC, audit and any model, where you own all the code and the data.**

Every fact about each framework below comes from its own repository, package registry or documentation, checked on 18 November 2026. Versions move weekly, so read them as a snapshot.

## Which open-source AI agent frameworks do enterprises actually shortlist in 2026?

Enterprises shortlist six agent frameworks in 2026: LangGraph, CrewAI, Microsoft Agent Framework, the OpenAI Agents SDK, the Claude Agent SDK and Google's Agent Development Kit (ADK). Five carry an OSI-approved licence; the sixth is a special case.

<table style="width:100%; border-collapse:collapse; margin:1.5rem 0; font-size:0.95rem;">
  <thead>
    <tr style="background:#f5f5f0; border-bottom:2px solid #2175C5;">
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Framework</th>
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Maintainer</th>
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Licence</th>
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Latest release (18 Nov 2026)</th>
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Commercial platform layer</th>
    </tr>
  </thead>
  <tbody>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong><a href="https://github.com/langchain-ai/langgraph">LangGraph</a></strong></td>
      <td style="padding:0.75rem;">LangChain</td>
      <td style="padding:0.75rem;">MIT</td>
      <td style="padding:0.75rem; font-variant-numeric:tabular-nums;">1.2.22 (14 Nov)</td>
      <td style="padding:0.75rem;">LangSmith Deployment</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong><a href="https://github.com/crewAIInc/crewAI">CrewAI</a></strong></td>
      <td style="padding:0.75rem;">CrewAI</td>
      <td style="padding:0.75rem;">MIT</td>
      <td style="padding:0.75rem; font-variant-numeric:tabular-nums;">1.15.42 (18 Nov)</td>
      <td style="padding:0.75rem;">CrewAI AMP Suite</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong><a href="https://pypi.org/project/agent-framework/">Microsoft Agent Framework</a></strong></td>
      <td style="padding:0.75rem;">Microsoft</td>
      <td style="padding:0.75rem;">MIT</td>
      <td style="padding:0.75rem; font-variant-numeric:tabular-nums;">Python 1.26.0 (12 Nov); 1.0 on 3 Apr 2026</td>
      <td style="padding:0.75rem;">Microsoft Foundry hosted agents</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong><a href="https://github.com/openai/openai-agents-python">OpenAI Agents SDK</a></strong></td>
      <td style="padding:0.75rem;">OpenAI</td>
      <td style="padding:0.75rem;">MIT</td>
      <td style="padding:0.75rem; font-variant-numeric:tabular-nums;">0.25.0 (18 Nov), pre-1.0</td>
      <td style="padding:0.75rem;">OpenAI tracing dashboard</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong><a href="https://github.com/anthropics/claude-agent-sdk-python">Claude Agent SDK</a></strong></td>
      <td style="padding:0.75rem;">Anthropic</td>
      <td style="padding:0.75rem;">MIT file; use under Anthropic Commercial Terms</td>
      <td style="padding:0.75rem; font-variant-numeric:tabular-nums;">0.2.184 (18 Nov)</td>
      <td style="padding:0.75rem;">Claude Managed Agents</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong><a href="https://github.com/google/adk-python">Google ADK</a></strong></td>
      <td style="padding:0.75rem;">Google</td>
      <td style="padding:0.75rem;">Apache 2.0</td>
      <td style="padding:0.75rem; font-variant-numeric:tabular-nums;">2.14.1 (12 Nov)</td>
      <td style="padding:0.75rem;">Agent Runtime on Gemini Enterprise Agent Platform</td>
    </tr>
  </tbody>
</table>

Releases are each project's Python package on PyPI. Microsoft's licence and version come from its PyPI package and its [1.0 announcement](https://devblogs.microsoft.com/agent-framework/microsoft-agent-framework-version-1-0/), which calls the framework "100% open source".

For Microsoft Agent Framework we cite the MIT-licensed package on PyPI for its licence and version.

## How do LangGraph, CrewAI and the other agent frameworks differ?

The six agent frameworks differ mainly in how they model state and who they assume you are. Each project's own README describes its centre of gravity.

- **LangGraph** calls itself "a low-level orchestration framework" for long-running, stateful agents, with durable execution, human-in-the-loop interrupts and short- and long-term memory.
- **CrewAI** orchestrates "role-playing, autonomous AI agents" as crews, with memory, knowledge, checkpointing and MCP/A2A support.
- **Microsoft Agent Framework** merged Semantic Kernel and AutoGen; its 1.0 covers .NET and Python, a graph workflow engine with checkpointing, YAML agent definitions and MCP.

- **OpenAI Agents SDK** is "provider-agnostic", supporting OpenAI's APIs "as well as 100+ other LLMs", with handoffs, guardrails, sessions, tracing and sandbox agents.
- **Claude Agent SDK** gives you "Claude Code as a library": built-in file and shell tools, hooks, subagents, permissions, sessions and MCP.
- **Google ADK** is code-first and, in its own words, "optimized for Gemini" yet "model-agnostic, deployment-agnostic".

For a deeper look at the Microsoft consolidation and what it means for where agents execute, see [the framework war is about who owns the agent runtime](/blog/microsoft-agent-framework-consolidation-vs-local-inference).

## Are all of these AI agent frameworks really open source and self-hostable?

Five of the six agent frameworks are open source under OSI-approved licences and run anywhere Python runs: LangGraph, CrewAI, Microsoft Agent Framework and the OpenAI Agents SDK under MIT, Google ADK under Apache 2.0. You can run every one of them on your own infrastructure.

The Claude Agent SDK is the exception worth reading twice.

Its repository ships an MIT licence file, but its README states that use "is governed by Anthropic's Commercial Terms of Service", and it runs the bundled Claude Code binary. It is public source built around one vendor's models.

Self-hostable library code is not the same as a self-hosted production platform. The framework's own hosted layer often carries different terms, which is where the next question starts.

## What does an open-source agent framework leave to you in production?

An open-source agent framework leaves the platform layer to you: who may use which agent, under which identity, with which model, and who changed it last. Each vendor's README points to a commercial product for exactly that layer.

CrewAI's README says organizations "that need a commercial control plane" get managed deployment, observability, governance and security from CrewAI AMP, with on-premise and cloud options. LangGraph's README points to LangSmith Deployment for production.

LangSmith documents four hosting options. Its cloud option "Requires a Plus plan or above", and the self-hosted control plane "Requires the Enterprise plan with Agent Server hosting enabled". A standalone Agent Server runs without a control plane but needs a LangSmith license.

<table style="width:100%; border-collapse:collapse; margin:1.5rem 0; font-size:0.95rem;">
  <thead>
    <tr style="background:#f5f5f0; border-bottom:2px solid #2175C5;">
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Production need</th>
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Open-source framework alone</th>
      <th style="text-align:left; padding:0.75rem; color:#5f6368;">Platform layer</th>
    </tr>
  </thead>
  <tbody>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong>SSO and role-based access</strong></td>
      <td style="padding:0.75rem;">You build it</td>
      <td style="padding:0.75rem;">Roles, policies, groups and teams per organization</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong>Audit trail</strong></td>
      <td style="padding:0.75rem;">Traces of runs; who changed the agent is yours to record</td>
      <td style="padding:0.75rem;">Per-agent log of who changed what and when</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong>Multi-tenant hosting</strong></td>
      <td style="padding:0.75rem;">You build it</td>
      <td style="padding:0.75rem;">Organization isolation with per-tenant configuration</td>
    </tr>
    <tr style="border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong>Model choice per agent</strong></td>
      <td style="padding:0.75rem;">In code, per deployment</td>
      <td style="padding:0.75rem;">An admin setting on each agent</td>
    </tr>
    <tr style="background:#f0f9ff; border-bottom:1px solid #e5e7eb;">
      <td style="padding:0.75rem;"><strong>Who owns that layer</strong></td>
      <td style="padding:0.75rem;">Your engineers, or the framework vendor's commercial plan</td>
      <td style="padding:0.75rem;"><strong>With ibl.ai, you: source code and data on your infrastructure</strong></td>
    </tr>
  </tbody>
</table>

None of this makes the frameworks weaker. It is a division of labour: a library decides how an agent thinks, a platform decides who may use it and on what terms.

## Where do open-source agent frameworks run in production with ibl.ai?

ibl.ai is the platform layer, and the frameworks fit inside it rather than compete with it. ibl.ai's own backend documentation lists a LangChain runtime layer that resolves registered MCP connections into LangChain tools at inference time.

On the ibl.ai platform each agent gets [role-based access](/docs/os/organization-settings/roles) built from roles and policies, an [audit log](/docs/os/agent-settings/audit) of who changed its model or tools, per-organization isolation, and an LLM picked per agent from any provider.

The link to whatever framework your team picks is MCP. An ibl.ai agent can attach any MCP server URL, and the hosted `iblai-agent-chat` MCP server lets any MCP client, including Claude Agent SDK code, hold a conversation with a deployed ibl.ai agent.

The [Agentic OS](/product/agentic-os) is the flagship that every agent runs on, and [Agentic Ontology](/product/agentic-ontology) serves your business terms to any agent as MCP servers from your own server. For agent runtimes such as OpenClaw, see the [OpenClaw service](/service/openclaw).

## Which parts of ibl.ai are open source, and which are licensed?

ibl.ai is part open source and part licensed, and the line is worth stating exactly. The application and toolkit repositories are public on GitHub under MIT: [iblai/os](https://github.com/iblai/os), [iblai/base](https://github.com/iblai/base), iblai/lms, iblai/infra-cli, [iblai/ontology](https://github.com/iblai/ontology) and the [.iblai agent standard](https://github.com/iblai/standard).

iblai/base (renamed from iblai/vibe on 18 November 2026) scaffolds a Next.js app on ibl.ai with SSO, AI chat and analytics, and ships the platform skills. The full catalogue is on the [developer hub](/developer).

The backend and infrastructure are not MIT. They come under a perpetual licence, and the complete source code is transferred in the Codebase Transfer engagement, priced as a "Custom quote" on the [pricing page](/pricing). The [full code license](/full-code-license) explains the terms.

## How should an enterprise choose an AI agent framework and a platform?

Choose the agent framework and the platform as two separate decisions, because they lock you into different things. Four questions settle both.

- **What language and state model does your team need?** Stateful graphs point to LangGraph or Microsoft Agent Framework; role-based crews to CrewAI; a light loop to the OpenAI Agents SDK; Google Cloud estates to ADK.
- **Do you need any model, or one vendor's?** OpenAI's SDK and Google ADK say in their READMEs that they work across model providers; the Claude Agent SDK is built for Claude.

- **Who will run SSO, RBAC and audit?** Your engineers, the framework vendor's commercial plan, or a platform you deploy.
- **Must you own that platform layer?** If the answer is yes, you need its source code, not an account on it.

For the platform-side comparison, including Copilot Studio, Bedrock AgentCore and watsonx Orchestrate, read [which platform should you use to build and deploy AI agents](/blog/which-platform-build-deploy-ai-agents-lock-in). For a head-to-head on one framework, see [ibl.ai vs LangGraph](/resources/comparisons/self-hosted-ai-vs-langgraph).

With ibl.ai you own all the code and the data: it is model-agnostic, carries no per-seat pricing, and you can deploy anywhere, from your own cloud to a fully air-gapped network.

ibl.ai is family-owned and operated from New York, NY, and our team stays on for updates and new agents after deployment.

## Why does owning the AI stack matter?

**ibl.ai is the agentic AI platform where you own all the code and the data. You self-host the entire stack inside your own perimeter, run it model-agnostic across any LLM and switch anytime, and pay by usage with no per-seat pricing — so you can deploy anywhere: your cloud, on-premise, GovCloud, or fully air-gapped.**

- **You own all the code and the data.** Full source code under a perpetual license, running on your infrastructure. Not API access to someone else's platform — the stack itself is yours.
- **Model-agnostic.** Run any LLM — Claude, GPT, Gemini, Llama, Command, or your own fine-tune — and switch providers without rewriting the platform.
- **No per-seat pricing.** Usage-based billing against a budget cap you set. Cost tracks what your organization actually uses, not how many people you employ.
- **Deploy anywhere.** Your cloud, your VPC, on-premise, GovCloud, or a fully air-gapped network with no outbound connectivity.

1.6M+ users across 400+ organizations run the platform this way, including NVIDIA, MIT, and Syracuse University.

ibl.ai is family-owned and operated from New York, NY — a U.S.-headquartered, domestically-owned long-term partner, not a vendor that sells licenses and moves on.

[Explore sovereigncorporation.ai](https://sovereigncorporation.ai/)
