9264866d1f
- Turborepo monorepo with apps/web and packages/database, sdk-python - Next.js 15 app with professional landing page (dark theme, emerald accent) - Prisma schema: Trace, DecisionPoint, Span, Event models with full indexing - Docker Compose: web (port 4200), postgres:16, redis:7, migrate service - Python SDK package stubs: init, trace decorator, log_decision, integrations - Multi-stage Dockerfile for standalone Next.js production build
39 lines
892 B
Markdown
39 lines
892 B
Markdown
# AgentLens Python SDK
|
|
|
|
AgentLens provides observability for AI agents by tracing decisions, not just API calls.
|
|
|
|
## Installation
|
|
|
|
```bash
|
|
pip install agentlens
|
|
```
|
|
|
|
## Quick Start
|
|
|
|
```python
|
|
from agentlens import init, trace
|
|
|
|
# Initialize AgentLens
|
|
init(api_key="your-api-key", endpoint="https://agentlens.vectry.tech")
|
|
|
|
# Trace your agent functions
|
|
@trace(name="research-agent")
|
|
async def research(topic: str) -> str:
|
|
return f"Researching: {topic}"
|
|
```
|
|
|
|
## Features
|
|
|
|
- **Decision Tracing**: Log and visualize agent decisions with alternatives
|
|
- **Context Awareness**: Monitor context window utilization
|
|
- **Cost Intelligence**: Track token usage and costs per operation
|
|
- **Integrations**: Native support for LangChain and OpenAI
|
|
|
|
## Documentation
|
|
|
|
Full documentation available at [https://agentlens.vectry.tech/docs](https://agentlens.vectry.tech/docs)
|
|
|
|
## License
|
|
|
|
MIT © 2026 Vectry
|