How shrisuha/agentic-ai-deck works
This small CrewAI starter runs a topic through a researcher and then a writer, printing the resulting brief. The main entry point checks the selected provider, then launches the crew; the crew selects a local model and can expose an optional word-count tool. A separate setup command finds or starts Ollama and downloads the configured model. The README documents the YAML-driven agent/task wiring and an OpenAI-compatible local-server option; unsampled YAML is represented from that documentation, not inspected directly.
Main entry points: crew.py Crew Orchestrator · main.py CLI Entry · llm.py Model Selection · ollama_server.py Server Discovery
Components 12
Brief Runtime
- CLI Entry
starter/main.py - Crew Orchestrator
starter/crew.py - Model Selection
starter/llm.py - Word Count Tool
starter/tools/example_tool.py
Crew Configuration
- Research Agent
starter/config/agents.yaml - Writer Agent
starter/config/agents.yaml - Task Definitions
starter/config/tasks.yaml
Local Models
- Model Setup
starter/setup.py - Server Discovery
starter/ollama_server.py
Other components
- User
- Ollama Server
- Compatible Server
Connections 13
- User → CLI Entry: runs topic
README.md - CLI Entry → Server Discovery: checks server
starter/main.py - CLI Entry → Crew Orchestrator: starts crew
starter/main.py - Crew Orchestrator → Research Agent: configures agent
README.md - Crew Orchestrator → Writer Agent: configures agent
README.md - Crew Orchestrator → Task Definitions: loads tasks
README.md - Research Agent → Writer Agent: passes notes
README.md - Crew Orchestrator → Model Selection: selects model
starter/crew.py - Model Selection → Ollama Server: targets model
starter/llm.py - Model Selection → Compatible Server: targets model
README.md - Crew Orchestrator → Word Count Tool: exposes tool
README.md - Model Setup → Server Discovery: ensures server
starter/setup.py - Server Discovery → Ollama Server: probes and pulls
starter/ollama_server.py