# Netra Documentation (llms.txt)

> Netra is the agent observability, evaluation, and simulation platform. This file is a copy/paste friendly overview + index of the Netra docs for LLMs.

## What is Netra?

Netra helps teams **trace**, **evaluate**, **simulate**, and **monitor** AI/LLM applications in development and production.

- **Observability (Traces & Spans)**: end-to-end visibility into prompts, model calls, tools, retrieval, latency, tokens, and cost
- **Evaluation**: datasets + evaluators (LLM-as-judge and code) + test runs for regression tracking
- **Simulation**: test agents in realistic multi-turn conversations with personas, goals, and session-level evaluation
- **Monitoring & Alerting**: dashboards + alert rules for cost, latency, and error thresholds
- **Multi-tenancy**: per-tenant / per-user / per-session context for SaaS apps
- **OpenTelemetry-based SDKs**: Python and TypeScript SDKs with auto-instrumentation and manual tracing

## Quick Start (fastest path)

1. Create an account, choose a data region, create an API key: `/quick-start/Overview`
2. Set environment variables (pick the endpoint for your region):

```bash
# US Region
export NETRA_OTLP_ENDPOINT="https://api.getnetra.ai/telemetry"
export NETRA_API_KEY="your-api-key-here"
```

```bash
# EU Region
export NETRA_OTLP_ENDPOINT="https://api.eu.getnetra.ai/telemetry"
export NETRA_API_KEY="your-api-key-here"
```

3. Install the SDK:

```bash
pip install netra-sdk
```

```bash
npm install netra-sdk
```

4. Initialize Netra at app startup:

```python
from netra import Netra

Netra.init(app_name="my-ai-app", environment="development")
```

```typescript
import { Netra } from "netra-sdk";

// TypeScript init is async — always await it.
await Netra.init({ appName: "my-ai-app", environment: "development" });
```

5. Make normal OpenAI/Anthropic/LangChain/etc calls — Netra will auto-instrument supported libraries.
6. View traces in the dashboard: `https://app.eu.getnetra.ai/login`

## Common SDK patterns (copy/paste)

### Context (tenant / user / session)

```python
from netra import Netra

Netra.set_tenant_id("tenant-123")
Netra.set_user_id("user-456")
Netra.set_session_id("session-789")
```

### Manual spans

```python
from netra import Netra, SpanType

with Netra.start_span("my-operation", as_type=SpanType.TOOL) as span:
    span.set_attribute("key", "value")
    # your code here
```

### Decorators

```python
from netra.decorators import workflow, agent, task

@workflow(name="my-workflow")
def my_workflow():
    pass

@agent(name="my-agent")
def my_agent():
    pass

@task(name="my-task")
def my_task():
    pass
```

## Docs Index (source-of-truth navigation)

Docs base: `https://docs.getnetra.ai`

### Documentation

- `/netra` (home)
- `/FAQs/FAQs`

#### Get Started
- `/quick-start/Overview`
- `/quick-start/QuickStart_Tracing`
- `/quick-start/QuickStart_Evals`
- `/quick-start/QuickStart_Simulation`
- `/quick-start/QuickStart_Alerts`

#### Observability
- Traces
  - `/Observability/Traces/overview`
  - `/Observability/Traces/spans`
  - `/Observability/Traces/auto-instrumentation`
  - `/Observability/Traces/decorators`
  - `/Observability/Traces/manual-tracing`
  - Configuration
    - `/Observability/Traces/configuration/initialization`
    - `/Observability/Traces/configuration/environment-variables`
    - `/Observability/Traces/configuration/instrumentation-selection`
    - `/Observability/Traces/configuration/custom-exporters`
- `/Observability/Tenants`
- `/Observability/Agents`
- `/Observability/Users`
- `/Observability/Session`

#### Evaluation
- `/Evaluation/Evaluation-overview`
- `/Evaluation/Evaluators`
- `/Evaluation/Datasets`
- `/Evaluation/TestRuns`

#### Simulation
- `/Simulation/Simulation-overview`
- `/Simulation/Evaluators`
- `/Simulation/Datasets`
- `/Simulation/TestRuns`

#### Monitoring & Dashboard
- `/Dashboard/Custom-dashboard`
- `/Alert-rules/Alert-rules`

#### Account settings
- `/Account-settings/Organisation`
- `/Account-settings/project`

#### MCP
- `/mcp/overview`
- `/mcp/skills`

### Integrations

- `/Integrations/overview`

#### LLM Frameworks
- `/Integrations/orchestrators/LangChain`
- `/Integrations/orchestrators/LangGraph`
- `/Integrations/orchestrators/LlamaIndex`
- `/Integrations/orchestrators/CrewAI`
- `/Integrations/orchestrators/PydanticAI`
- `/Integrations/orchestrators/LiteLLM`
- `/Integrations/orchestrators/Haystack`
- `/Integrations/orchestrators/DSPy`
- `/Integrations/orchestrators/MCP`
- `/Integrations/orchestrators/ADK`
- `/Integrations/orchestrators/Cerebras`

#### Model Providers
- `/Integrations/ai_providers/OPENAI`
- `/Integrations/ai_providers/ANTHROPIC_CLAUDE`
- `/Integrations/ai_providers/GEMINI`
- `/Integrations/ai_providers/AWS_BEDROCK`
- `/Integrations/ai_providers/MISTRAL`
- `/Integrations/ai_providers/GROQ`
- `/Integrations/ai_providers/COHERE`
- `/Integrations/ai_providers/VERTEXAI`
- `/Integrations/ai_providers/OLLAMA`
- `/Integrations/ai_providers/TOGETHERAI`
- `/Integrations/ai_providers/REPLICATE`
- `/Integrations/ai_providers/HUGGINGFACE_TRANSFORMERS`
- `/Integrations/ai_providers/ALEPH_ALPHA`
- `/Integrations/ai_providers/WATSONX`

#### Vector Databases
- `/Integrations/db-docs/Pinecone`
- `/Integrations/db-docs/CHROMA`
- `/Integrations/db-docs/Weavite`
- `/Integrations/db-docs/Qdrant`
- `/Integrations/db-docs/Milvus`
- `/Integrations/db-docs/Redis`
- `/Integrations/db-docs/LanceDB`
- `/Integrations/db-docs/Margo`

#### Speech-to-Text & Text-to-Speech
- `/Integrations/stt-tts-docs/Cartesia`
- `/Integrations/stt-tts-docs/Deepgram`
- `/Integrations/stt-tts-docs/Elevenlabs`

### SDK (integration + API reference)

#### SDK Overview Pages
- `/sdk/overview`
- `/sdk/python`
- `/sdk/typescript`

#### SDK API Reference Pages
- Usage, Traces & Spans
  - `/sdk-reference/usage/python`
  - `/sdk-reference/usage/typescript`
- Dashboard Query
  - `/sdk-reference/dashboard-query/python`
  - `/sdk-reference/dashboard-query/typescript`
- Evaluation
  - `/sdk-reference/evaluation/python`
  - `/sdk-reference/evaluation/typescript`
- Simulation
  - `/sdk-reference/simulation/python`
  - `/sdk-reference/simulation/typescript`
- SDK Reference
  - `/sdk-reference/sdk/overview`
  - `/sdk-reference/sdk/python`
  - `/sdk-reference/sdk/typescript`

### Cookbooks

#### Observability
- `/Cookbooks/observability/tracing-rag-pipeline`
- `/Cookbooks/observability/tracing-langchain-agents`
- `/Cookbooks/observability/tracing-crewai-pipelines`
- `/Cookbooks/observability/multi-tenant-cost-tracking`

#### Evaluation
- `/Cookbooks/evaluation/evaluating-rag-quality`
- `/Cookbooks/evaluation/evaluating-agent-decisions`
- `/Cookbooks/evaluation/ab-testing-configurations`

### Additional pages present in this repo

#### Tutorials
- `/Tutorials/custom-trace-views`
- `/Tutorials/comparing-traces`

#### Privacy & Security (SDK)
- `/privacy-security/pii-detection`
- `/privacy-security/input-scanners/prompt-injection`

## External Links

- Website: `https://getnetra.ai/`
- Docs: `https://docs.getnetra.ai/`
- Dashboard login: `https://app.eu.getnetra.ai/login`
- Python SDK (PyPI): `https://pypi.org/project/netra-sdk/`
- TypeScript SDK (npm): `https://www.npmjs.com/package/netra-sdk`
- GitHub Python-SDK: `https://github.com/KeyValueSoftwareSystems/netra-sdk-py`
- GitHub TypeScript-SDK: `https://github.com/KeyValueSoftwareSystems/netra-sdk-js`