Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vaultak.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Step 1: Install

```bash pip install vaultak ```

​
Step 2: Get your API key

Sign up at app.vaultak.com. Your API key is on the API Key tab. It starts with vtk_.

​
Step 3: Wrap your agent

```python from vaultak import Vaultak vt = Vaultak(api_key=“vtk_your_api_key_here”) with vt.monitor(“my-agent”): agent.run() ``` Every action your agent takes is now monitored, risk-scored, and logged in real time. Node.js: 
const { Vaultak } = require("vaultak");

const vt = new Vaultak({ apiKey: "vtk_your_api_key_here" });
vt.monitor("my-agent");

myAgent.run();

​
Step 4: Configure thresholds

```python vt = Vaultak( api_key=“vtk_your_api_key_here”, alert_threshold=30, # Score >= 30: alert and log pause_threshold=60, # Score >= 60: halt agent, await review rollback_threshold=85 # Score >= 85: auto-rollback and halt ) ```

​
Step 5: Define what your agent is allowed to do

```python vt = Vaultak( api_key=“vtk_your_api_key_here”, allowed_resources=[“/tmp/”, “/data/readonly/”], blocked_resources=[“prod.”, “.env”, “*.key”], max_actions_per_minute=20, ) ``` Policies can also be created and managed in the dashboard — no code changes needed.

​
Response modes

ModeTriggerBehavior
AlertScore >= 30Logs event, sends notification, agent continues
PauseScore >= 60Halts agent, queues action for human review
RollbackScore >= 85Reverses state using snapshot, halts agent

​
Works with any framework

```python

​
LangChain

with vt.monitor(“langchain-agent”): response = llm.invoke(prompt)

​
CrewAI

with vt.monitor(“crew-agent”): crew.kickoff()

​
AutoGen

with vt.monitor(“autogen-agent”): agent.run() ```

​
Environment variable

```bash export VAULTAK_API_KEY=vtk_your_api_key_here ``` ```python vt = Vaultak() # Reads from VAULTAK_API_KEY automatically ```

​
Next steps