NOTES / FRAMEWORKS AND SDKS

Choosing a framework

How to compare agent frameworks: what layer each occupies, which problems each is built for, and a short list of questions that decide the choice.

UPDATED 18 NOV 2026#frameworks#comparison#selection

Frameworks differ in kind

“Agent framework” covers tools that sit at different layers. LangChain’s own docs separate three: a runtime (LangGraph) for durable execution, streaming, human-in-the-loop and persistence; a framework for model, tool and agent-loop abstractions; and a harness (Deep Agents) that adds planning, subagents, file tools and context management on top2. Comparing a runtime with a harness is like comparing a database with an application.

Diagram: layers from model API up through runtime and framework to harness

Diagram: my own. The layer names follow the split LangChain describes in 2; other vendors draw the lines differently.

What each is built for

A quick orientation, drawn from each project’s own documentation. Details are in the linked notes.

Option Core idea Notes
LangGraph Graphs of shared state, nodes and edges with checkpointing2 Low-level; strong on durability and human-in-the-loop
OpenAI Agents SDK Small set of primitives: agents, handoffs, guardrails, sessions, tracing3 Lightweight
Claude Agent SDK Claude Code’s agent loop and tools as a library4 Strong for coding and file work
Google ADK LLM agents plus Sequential, Parallel and Loop workflow agents5 Multi-language
CrewAI Agents, crews and flows6 Role-based teams plus event-driven flows
Pydantic AI Typed agents with dependency injection and validated output7 Python, type-focused

Questions that decide it

Diagram: needs mapped to types of framework: graph runtime, agent SDK, handoff-style SDK, typed framework, or plain API calls

Diagram: my own rough guide, not a ranking.

  1. Do you need durable, resumable state? Long-running work and human approval pauses favour a runtime with checkpointing.
  2. Is the work mostly code or files? A harness with built-in file and shell tools saves building them.
  3. Is the control flow fixed or model-chosen? Workflow-style primitives suit fixed paths; agent loops suit open-ended ones (Workflows versus agents).
  4. Which model providers must you support? Some SDKs are tied to one provider by default; check how model-agnostic each really is.
  5. How will you test and trace? Look for built-in tracing, and for testability such as typed dependencies you can fake.
  6. How much of the framework can your team read? Anthropic’s advice is to understand what is under the hood1.
  7. Language and deployment. Python, TypeScript, Go and Java support differ by project.

Cautions

  • The field moves quickly. Names, APIs and recommended patterns change within months. Check each project’s current docs before committing; I have kept the claims here to ones the docs make.
  • Lock-in is mostly in your prompts and tools, not the loop. Keep tool implementations and prompts portable and the framework swap is cheaper.
  • Pilot on a thin slice. Build one real workflow in your top two candidates and compare effort, traces and failure behaviour. Measure with the same eval set.
  • Do not use several at once without a reason; each adds its own abstractions.

If none of this decides it, build without one (Building without a framework) and revisit.

Sources

  1. [1]Building effective agents — Anthropic · 2024PARAPHRASED
  2. [2]LangGraph overview — LangChain docsPARAPHRASED
  3. [3]OpenAI Agents SDK — OpenAIPARAPHRASED
  4. [4]Agent SDK overview — Anthropic, Claude Code docsPARAPHRASED
  5. [5]Agent Development Kit docs — GooglePARAPHRASED
  6. [6]CrewAI documentation — CrewAIPARAPHRASED
  7. [7]Pydantic AI — PydanticPARAPHRASED

© Ashish Kumar. All rights reserved. Quoted and cited material belongs to its owners. How I attribute sources.

Product, company and framework names are trademarks of their respective owners. Mentioning them does not imply affiliation or endorsement.