plano/demos/use_cases/multi_frameworks/README.md

26 lines
1 KiB
Markdown
Raw Normal View History

2026-01-16 13:10:03 -08:00
# Multi-Framework Travel Agents
2026-01-16 17:04:17 -08:00
This demo shows how Plano orchestrates multiple agents built on different frameworks. We run a CrewAI flight agent and a LangChain weather agent side by side to highlight that Plano is frameworkagnostic while still providing a consistent gateway for requests, tools, and telemetry.
2026-01-16 13:10:03 -08:00
2026-01-16 17:04:17 -08:00
## How it works
2026-01-16 13:10:03 -08:00
2026-01-16 17:04:17 -08:00
Plano sits between clients and agents. Each agent runs independently and exposes its own tools and behavior. The gateway routes requests to the right agent, normalizes requests/responses, and keeps orchestration consistent across frameworks without coupling them together.
2026-01-16 13:10:03 -08:00
2026-01-16 17:04:17 -08:00
## Agents
2026-01-16 17:02:21 -08:00
2026-01-16 17:04:17 -08:00
- **CrewAI Flight Agent** (Port 10520): flight search and itineraries
- **LangChain Weather Agent** (Port 10510): weather forecasts and conditions
2026-01-16 17:02:21 -08:00
2026-01-16 17:04:17 -08:00
## Quick start
2026-01-16 13:10:03 -08:00
```bash
2026-01-16 17:04:17 -08:00
docker compose build
2026-01-16 13:10:03 -08:00
docker compose up -d
```
2026-01-16 17:02:21 -08:00
## Environment variables
2026-01-16 17:04:17 -08:00
- `OPENAI_API_KEY`: required for LLM access
- `AEROAPI_KEY`: optional for flight data
- `LLM_GATEWAY_ENDPOINT`: Plano gateway endpoint (default: http://host.docker.internal:12000/v1)