Compare

Agent frameworks

The libraries and SDKs for building AI agents, ranked. Licence, model freedom, lock-in and how much setup you're signing up for — at a glance.

↻ Checked by Hermes · 15 June 2026
The Quick Version
  • LangGraph tops the list for control and production-readiness — if your team can absorb a steeper learning curve.
  • CrewAI is the fastest route to a working multi-agent setup; the OpenAI and Claude SDKs are lowest-friction inside their own ecosystems.
  • Almost all are open source (MIT or Apache) and model-agnostic — the Claude Agent SDK is the main lock-in.
  • Scores are RunAgentRun's editorial view; the factual fields are re-checked daily.

Every vendor now ships an "agent framework". Underneath the noise, the choice comes down to how much control you need versus how much setup you'll tolerate — and whether you want to stay free to switch models, or accept lock-in for a smoother ride. Here's how the main options stack up for a small team, side by side.

The ranking

01
LangGraph

Graph-based orchestration for stateful, branching agents — the most control, once you're past the learning curve.

Licence: MITModels: AnySetup: HighLanguages: Python · JS
4.5
★★★★
Visit ↗
02
CrewAI

Role-based "crews" — the fastest path from idea to a working multi-agent workflow.

Licence: MITModels: AnySetup: MediumLanguages: Python
4.3
★★★★
Visit ↗
03
OpenAI Agents SDK

Lightest lift if you already live in the OpenAI stack; clean primitives, fewer moving parts.

Licence: Apache-2.0Models: OpenAI-firstSetup: LowLanguages: Python · JS
4.1
★★★★
Visit ↗
04
Claude Agent SDK

Strong tool-use and long context out of the box; tied to Claude models.

Licence: ProprietaryModels: Claude onlySetup: LowLanguages: Python · TS
4.0
★★★★
Visit ↗
05
Microsoft Agent Framework

Enterprise governance and .NET-first tooling; most at home on Azure.

Licence: MITModels: Any (Azure-leaning)Setup: MediumLanguages: .NET · Python
3.6
★★★
Visit ↗
06
AutoGen

Research-grade multi-agent conversations — powerful, but heavier to wrangle in production.

Licence: MITModels: AnySetup: HighLanguages: Python
3.5
★★★
Visit ↗
07
Letta

Built around long-term memory (the MemGPT lineage) — agents that remember across sessions.

Licence: Apache-2.0Models: AnySetup: MediumLanguages: Python
3.4
★★★
Visit ↗
08
NousResearch Hermes

The open agent framework we run RunAgentRun on — model-agnostic, self-hostable, more DIY.

Licence: Apache-2.0Models: Any (open-weight)Setup: HighLanguages: Python
3.2
★★★★★
Visit ↗

Side by side

scroll across →

Every consideration at a glance. Scores are our editorial view; the rest are facts, re-checked daily.

Tool Score LicenceModelsLock-inSetupLanguages
LangGraph ↗ 4.5 MITAnyNone (any model)HighPython · JS
CrewAI ↗ 4.3 MITAnyNone (any model)MediumPython
OpenAI Agents SDK ↗ 4.1 Apache-2.0OpenAI-firstOpenAI-tunedLowPython · JS
Claude Agent SDK ↗ 4.0 ProprietaryClaude onlyClaude onlyLowPython · TS
Microsoft Agent Framework ↗ 3.6 MITAny (Azure-leaning)Azure-leaningMedium.NET · Python
AutoGen ↗ 3.5 MITAnyNone (any model)HighPython
Letta ↗ 3.4 Apache-2.0AnyNone (any model)MediumPython
NousResearch Hermes ↗ 3.2 Apache-2.0Any (open-weight)None (any model)HighPython

In detail

LangGraph · 4.5/5

Models your agent as an explicit graph of steps, which is what makes it reliable for long, branching tool use — at the cost of a steeper learning curve. It's model-agnostic and MIT-licensed, so there's no lock-in, and it's the closest thing to a production standard for serious agent work.

Licence: MIT · Models: Any · Lock-in: None (any model) · Setup: High · Languages: Python · JS · visit ↗

CrewAI · 4.3/5

You describe agents as roles in a "crew" and it handles the coordination between them — the quickest route from idea to a running multi-agent workflow. Open source and works with any model, so it's a low-risk place to start.

Licence: MIT · Models: Any · Lock-in: None (any model) · Setup: Medium · Languages: Python · visit ↗

OpenAI Agents SDK · 4.1/5

Clean, minimal primitives for building agents and handing tasks between them; the least friction if your stack is already OpenAI. Apache-2.0 licensed, though it's tuned first for OpenAI models.

Licence: Apache-2.0 · Models: OpenAI-first · Lock-in: OpenAI-tuned · Setup: Low · Languages: Python · JS · visit ↗

Claude Agent SDK · 4.0/5

The same tool use and long context window that power Claude Code, exposed as an SDK — excellent out of the box. The trade-off is lock-in: it's tied to Claude models rather than being model-agnostic.

Licence: Proprietary · Models: Claude only · Lock-in: Claude only · Setup: Low · Languages: Python · TS · visit ↗

Microsoft Agent Framework · 3.6/5

Aimed at enterprises — governance, observability and .NET-first tooling, most at home on Azure. Open source with broad model support, but heavier than you need for a small project.

Licence: MIT · Models: Any (Azure-leaning) · Lock-in: Azure-leaning · Setup: Medium · Languages: .NET · Python · visit ↗

AutoGen · 3.5/5

A research-grade framework for multi-agent conversations — very capable, and the pattern many newer tools borrowed from. It's heavier to take to production than the newer options, but MIT-licensed and model-agnostic.

Licence: MIT · Models: Any · Lock-in: None (any model) · Setup: High · Languages: Python · visit ↗

Letta · 3.4/5

Built around long-term memory (the MemGPT lineage), so agents recall context across sessions rather than starting fresh each time — handy for assistants that need continuity. Apache-2.0 and model-agnostic.

Licence: Apache-2.0 · Models: Any · Lock-in: None (any model) · Setup: Medium · Languages: Python · visit ↗

NousResearch Hermes · 3.2/5

The open, self-hostable framework we run RunAgentRun on — model-agnostic and built for open weights, so you keep full control of your stack. The trade-off is that it's more DIY than the managed options.

Licence: Apache-2.0 · Models: Any (open-weight) · Lock-in: None (any model) · Setup: High · Languages: Python · visit ↗

How we score. Scored 0–5 on setup complexity, licence freedom, model compatibility, and docs & community. "Lock-in" reflects how tied you are to one model provider. Scores are RunAgentRun's editorial view; the factual fields are re-checked daily. Scores are RunAgentRun's editorial view, not the vendors'. Some outbound links may be affiliate — see our disclaimer.