Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 41 additions & 0 deletions docs/integrations/callbacks/suprawall.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
---
sidebar_label: SupraWall
---

# SupraWall

[SupraWall](https://www.supra-wall.com) is a deterministic security and compliance layer for AI agents. It provides a zero-trust runtime protection system that intercepts tool calls and validates them against enterprise-grade policies before execution.

Key features include:
- **Human-in-the-loop (HITL) Approvals**: Explicitly require human authorization for destructive or high-value tool calls.
- **EU AI Act Compliance**: Automated logging (Article 12) and risk management (Article 9) for high-risk AI systems.
- **Prompt Injection Defense**: Intercepts adversarial intent at the tool-execution boundary.
- **Tamper-proof Audit Logs**: Forensic-grade records of all agent actions.

## Installation

Install the library via pip:

```bash
pip install langchain-suprawall
```

## Using the Callback Handler

```python
from langchain_suprawall import SupraWallCallbackHandler
from langchain.agents import AgentExecutor

# Initialize the callback
suprawall = SupraWallCallbackHandler(agent_id="customer-service-bot")

agent_executor = AgentExecutor(
agent=agent,
tools=tools,
callbacks=[suprawall]
)
```

## Related
- [SupraWall Documentation](https://docs.supra-wall.com)

Loading