Yashotantra Academy logo
← AI Agents & MCP theorytheory 0/14 · 0%
level 1
Curious · 0 XP
streak
0d
perfect
0
badges
0

100 XP to Apprentice

Tooling · medium

9. Framework landscape: LangGraph, CrewAI, AutoGen, Agno

What each framework optimises for, and when plain code is better.

1 min read2 questionsup to 50 XPtopic 9/14

Read in another language

AI translates the explanation and quiz text while preserving code and answer scoring.

- LangGraph — agents as explicit state graphs with nodes, edges, checkpointing, and human-in-the-loop interrupts. Best when you need durable, resumable, auditable workflows. - CrewAI — role-based crews (`role`, `goal`, `backstory`) with sequential or hierarchical processes. Fast to express "team of specialists" products. - AutoGen / AG2 — conversation-centric multi-agent chat, strong for code-executing agents in sandboxes. - LlamaIndex — retrieval-first agents over indexed corpora. - Agno, CAMEL, AWS Strands — lightweight or provider-aligned runtimes.

python
from langgraph.graph import StateGraph, END

g = StateGraph(State)
g.add_node("plan", plan_node)
g.add_node("act", act_node)
g.add_conditional_edges("act", lambda s: "act" if s["pending"] else END)
g.set_entry_point("plan")
app = g.compile(checkpointer=saver)   # resumable across process restarts

Adopt a framework for what is genuinely hard: durable state, checkpoint/resume, human approval gates, and tracing. A single-tool assistant does not need one — a 60-line loop is easier to debug and cheaper to run.

Exercise: rebuild your loop in LangGraph with a checkpointer, kill the process mid-run, and resume from the last checkpoint.

How to study this topic

  1. 1. Read the explanation once end to end, skipping the code.
  2. 2. Re-read the code snippets and say out loud what each line does.
  3. 3. Answer the quiz without scrolling back — that is the real check.
  4. 4. Read every explanation, even for the answers you got right.

Scoring

  • · Up to 30 XP from quiz accuracy.
  • · +15 XP for a perfect first attempt.
  • · +5 XP while a 3-day streak is running.
  • · 75% or higher marks the topic complete.

Check your understanding

  1. 1. Which framework models agents as an explicit, checkpointable state graph?

  2. 2. Strongest reason to adopt an agent framework?

Badges

First light
Pass your first topic
Sharp shooter
3 perfect first-try quizzes
On a roll
Study 3 days in a row
Week warrior
Study 7 days in a row
Grinder
Earn 500 XP
Deep diver
Earn 1500 XP