langchain-ai/deep-agents-from-scratch

• highabout#1

  Add a concise repository description

  Why:

  COPY-PASTE FIX

  Copy

  A course demonstrating how to implement advanced AI agent design patterns from scratch using LangGraph, focusing on task planning, context offloading, and sub-agent delegation.

  OpenDoneDismiss
• mediumreadme#2

  Reposition README's educational focus

  Why:

  CURRENT

  # 🧱 Deep Agents from Scratch
  
  Deep Research broke out as one of the first major agent use-cases along with coding. Now, we've seeing an emergence of general purpose agents that can be used for a wide range of tasks. For example, Manus has gained significant attention and popularity for long-horizon tasks; the average Manus task uses ~50 tool calls!. As a second example, Claude Code is being used generally for tasks beyond coding. Careful review of the context engineering patterns across these popular "deep" agents shows some common approaches:
  
  Task planning (e.g., TODO), often with recitationContext offloading to file systemsContext isolation through sub-agent delegation**
  
  This course will show how to implement these patterns from scratch using LangGraph!

  COPY-PASTE FIX

  Copy

  # 🧱 Deep Agents from Scratch: A LangGraph Course
  
  This course teaches how to implement advanced AI agent design patterns from scratch using LangGraph. We'll explore common approaches seen in popular "deep" agents, such as task planning, context offloading to file systems, and context isolation through sub-agent delegation, enabling you to build robust, general-purpose agents for complex, long-horizon tasks.

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  How to build AI agents that handle complex, long-horizon tasks with planning?

  you: not recommended
  AI recommended (in order):

  1. LangChain
  2. LlamaIndex
  3. Haystack
  4. AutoGPT
  5. BabyAGI
  6. mcts
  7. Pylot
  8. GAMA

  AI recommended 8 alternatives but never named langchain-ai/deep-agents-from-scratch. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  What are common design patterns for building robust, general-purpose AI agents in Python?

  you: not recommended
  AI recommended (in order):

  1. LangChain (langchain-ai/langchain)
  2. LlamaIndex (run-llama/llama_index)
  3. CrewAI (joaomdmoura/crewAI)
  4. AutoGen (microsoft/autogen)
  5. Jinja2 (pallets/jinja)

  AI recommended 5 alternatives but never named langchain-ai/deep-agents-from-scratch. This is the gap to close.

  Show full AI answer

• Metadata completeness

  fail

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of langchain-ai/deep-agents-from-scratch?

  pass
  ✓AI named langchain-ai/deep-agents-from-scratch explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts langchain-ai/deep-agents-from-scratch in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named langchain-ai/deep-agents-from-scratch explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo langchain-ai/deep-agents-from-scratch solve, and who is the primary audience?

  pass
  ⚠AI did not name langchain-ai/deep-agents-from-scratch — likely talking about a different project

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?