> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tracectrl.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Security observability and control for agentic AI systems

# TraceCtrl

TraceCtrl gives security teams and developers complete visibility into every agent action, tool call, and data access — with runtime protection and attack graph risk scoring.

Built by [CloudsineAI](https://www.cloudsine.tech).

## What TraceCtrl Does

> [card] Agent Visibility
>
> See every LLM call, tool invocation, and agent-to-agent message in real time. Know exactly what your agents are doing.

> [card] Security Enrichment
>
> Every span is enriched with security attributes — tool risk categories, input provenance, session correlation, and prompt drift detection.

> [card] Topology Mapping
>
> Automatically discovers agent-to-agent and agent-to-tool relationships, building a live topology graph of your agentic system.

> [card] Risk Scoring
>
> TAGAAI-powered attack graph analysis scores agents and paths by exploitability — prompt injection, excessive agency, data leakage.

## How It Works

TraceCtrl uses OpenTelemetry as the transport layer. You add 3 lines to your agent code, and the SDK captures every operation as enriched spans.

```python theme={"dark"}
import tracectrl
tracectrl.configure(service_name="my-agent")
tracectrl.tag_agent(name="my-agent", role="primary")

from tracectrl.instrumentation.strands import StrandsInstrumentor
StrandsInstrumentor().instrument()

# Your existing agent code — no changes needed
```

Spans flow through the OTel Collector into ClickHouse, where the TraceCtrl Engine processes them into an agent inventory, topology graph, and risk scores — all queryable via API and visible in the dashboard.

## Supported Frameworks

| Framework | Package | Version | Downloads | Status |
| - | - | - | - | - |
| Agno | `tracectrl-instrumentation-agno` | [![PyPI](https://img.shields.io/pypi/v/tracectrl-instrumentation-agno?color=blue\&label=)](https://pypi.org/project/tracectrl-instrumentation-agno/) | [![Downloads](https://img.shields.io/pypi/dm/tracectrl-instrumentation-agno?color=blue\&label=)](https://pypistats.org/packages/tracectrl-instrumentation-agno) | Stable |
| AWS Strands | `tracectrl-instrumentation-strands` | [![PyPI](https://img.shields.io/pypi/v/tracectrl-instrumentation-strands?color=blue\&label=)](https://pypi.org/project/tracectrl-instrumentation-strands/) | [![Downloads](https://img.shields.io/pypi/dm/tracectrl-instrumentation-strands?color=blue\&label=)](https://pypistats.org/packages/tracectrl-instrumentation-strands) | Stable |
| CrewAI | `tracectrl-instrumentation-crewai` | — | — | Source only |
| LangChain | `tracectrl-instrumentation-langchain` | — | — | Source only |
| Google ADK | `tracectrl-instrumentation-google-adk` | — | — | Source only |
| OpenClaw | Native OTEL — no SDK needed | — | — | Stable |

> [!NOTE]
>
> **Stable** = published to PyPI and tested end-to-end.
> **Source only** = the instrumentor package exists in the TraceCtrl repo and can be installed from source (`pip install -e ./sdk/tracectrl-instrumentation-<framework>`), but is not yet on PyPI.
> OpenClaw uses its native OTEL export — no TraceCtrl SDK needed. See the [OpenClaw instrumentor guide](https://docs.tracectrl.ai/instrumentors/openclaw.md).

## Next Steps

> [card] [Quickstart](https://docs.tracectrl.ai/quickstart.md)
>
> Get TraceCtrl running in 5 minutes with Docker Compose.

> [card] [SDK Installation](https://docs.tracectrl.ai/sdk/installation.md)
>
> Install the SDK and instrument your first agent.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.