How ayushtiwari134/linkedin_agent works
This is a small CrewAI application that generates a LinkedIn post through research, drafting, and humanization. The run is configured and started in crew.py; task definitions assign each stage to an agent, and the final task writes linkedin_post.txt. Agent definitions configure a shared local ChatOpenAI endpoint. The workflow is supported by the sampled source; the README describes the same stages. tools.py is empty, so it is not represented.
Main entry points: crew.py Sequential Crew · tasks.py Humanizing Task · agents.py Chat Model · linkedin_post.txt Generated Post
Components 11
Orchestration
- Crew Runner
crew.py - Sequential Crew
crew.py
Content Workflow
- Research Task
tasks.py - Research Agent
agents.py - Writing Task
tasks.py - Post Writer
agents.py - Humanizing Task
tasks.py - Humanizer Agent
agents.py
Model Runtime
- Chat Model
agents.py
Other components
- Generated Post
linkedin_post.txt - Console
Connections 12
- Crew Runner → Sequential Crew: starts
- Sequential Crew → Research Task: runs first
- Sequential Crew → Writing Task: runs next
- Sequential Crew → Humanizing Task: runs last
- Research Task → Research Agent: assigned to
- Writing Task → Post Writer: assigned to
- Humanizing Task → Humanizer Agent: assigned to
- Research Agent → Chat Model: uses
- Post Writer → Chat Model: uses
- Humanizer Agent → Chat Model: uses
- Humanizing Task → Generated Post: writes output
- Crew Runner → Console: prints result