pf-06-aethercrew-ai-company
A hand-built orchestrator that assigns work, picks models, and tracks cost for 11 AI employees in a virtual company. Agent work is simulated and no language model API is called.
- Python
- FastAPI
- WebSocket
- pytest
- Slack
- Jira
- GitHub
- 11
- AI employees
- 3
- Divisions
- 8
- Dashboard pages
Approach
The chief of staff takes a CEO directive, writes a plan, and splits it into tasks by role. Each employee has a priority list of Anthropic, OpenAI, Google, and DeepSeek models and moves to the next on failure. Estimated costs add up, with warnings at 80% and 95% and work stopped at 100%. External writes are off by default, and file access stays inside the project root.
View on GitHub ↗
Open the case: case-studies/aethercrew/README.md →