← All agents

AI & research · One purpose, multiple implementations

YouTube Comment Sentiment Analyzer

Adapt the published “YouTube Comment Sentiment Analyzer” workflow to other implementations while preserving its documented behavior.

The source contains 14 executable nodes and 16 connections. This draft is derived from the n8n export; it needs a human-reviewed purpose, input/output contract, and behavioral tests before a port can claim equivalence.

Open agent files on GitHub ↗

Shared workflow

This initial Mermaid diagram shows observed connections from the n8n source, including model and tool dependencies. Unresolved connections are listed under Evidence. It is a starting point for the shared design; it does not execute the agent or establish correctness.

Rendering the workflow diagram…

Read the Mermaid source
flowchart LR
  n0["Split Out"]
  n1["OpenAI Chat Model"]
  n2["No Operation, do nothing"]
  n3["Get Video Urls from Google Sheet"]
  n4["check next fetch time is available or not"]
  n5["check next fetch time is before the current time"]
  n6["Get Comments for video urls"]
  n7["Analyze sentiment of every comment"]
  n8["Format fields as required to save in google sheet"]
  n9["Insert and update comment in google sheet"]
  n10["Update last fetched time and next_fetch_time"]
  n11["No Operation, do nothing1"]
  n12["When clicking #8216;Test workflow#8217;"]
  n13["Check Success Response"]
  n0 -->|"main out 0 to in 0"| n7
  n1 -->|"ai_languageModel out 0 to in 0"| n7
  n13 -->|"main out 0 to in 0"| n0
  n13 -->|"main out 1 to in 0"| n11
  n6 -->|"main out 0 to in 0"| n13
  n3 -->|"main out 0 to in 0"| n4
  n12 -->|"main out 0 to in 0"| n3
  n7 -->|"main out 0 to in 0"| n8
  n7 -->|"main out 1 to in 0"| n8
  n7 -->|"main out 2 to in 0"| n8
  n9 -->|"main out 0 to in 0"| n10
  n4 -->|"main out 0 to in 0"| n6
  n4 -->|"main out 1 to in 0"| n5
  n5 -->|"main out 0 to in 0"| n6
  n5 -->|"main out 1 to in 0"| n2
  n8 -->|"main out 0 to in 0"| n9
Read the specification and unresolved requirements ↗

Implementations

Each implementation shares the agent’s purpose. Available source, planned ports, and verified results are labeled separately.

Plain Python

Planned · no code yet

Read the implementation plan ↗

Pydantic AI

Planned · no code yet

Read the implementation plan ↗

CrewAI Flow

Planned · no code yet

Read the implementation plan ↗

CrewAI Crew

Planned · no code yet

Read the implementation plan ↗

LangGraph

Planned · no code yet

Read the implementation plan ↗

Build or operate with an assistant

Each prompt includes separate build and operating instructions tailored to this agent. They are untested instructions, not working implementations. Check the chosen product’s actual capabilities before using it.

Evidence and remaining work

The bulk collection has publication checks, not live-service testing. Diagrams and prompts are documentation. A port needs reviewed schemas, fixtures, actual execution results, and explicit limits before claiming equivalent behavior.

  • Define input/output schemas and expected outputs.
  • Review source expressions, external actions, and failure behavior.
  • Determine whether model judgment is required or deterministic rules suffice.

Curated by Nik Bear Brown. Preserve each implementation’s original attribution and license. These source templates are separate from the audited Claude directory.