Introduction
Tawa Guard inspects prompts for injection and other attacks before they reach your LLM. Pick TypeScript, Python, or the raw API.
Tawa Guard is a developer platform that scans text — typically user input headed for an LLM, retrieved RAG content, or agent tool traffic — and returns a decision: allow it, flag it for review, or block it. It catches prompt injection, jailbreaks, prompt-extraction attempts, tool-injection, and obfuscated attacks.
You integrate over a REST API or the typed SDKs. Submit text, get back a decision with a confidence score and a human-readable rationale.
Pick your integration
TypeScript
@tawaguard/sdk — a fully-typed client, a live event stream, and Vercel AI SDK middleware.
Python
tawaguard-sdk: sync and async clients, plus OpenAI Agents SDK guardrails, including tool call and tool result scanning.
Claude Code
No integration code — run a local relay in front of the Claude Code CLI instead.
Codex
Same idea for Codex CLI — a local relay in front of the OpenAI Responses API.
API Reference
The raw REST API, endpoint-by-endpoint, with rate limiting and retry guidance for building your own client.
Not using TypeScript or Python? The API Reference is written for exactly that — the full endpoint reference plus best practices (rate limits, retries, timeouts) so you can build a client that behaves the same way the official SDKs do.
Current versions
| Component | Version | Released |
|---|---|---|
| Dashboard | 1.0.0 | 31 October 2026 |
| Gateway | 1.0.0 | 31 October 2026 |
| Proxy | 1.0.0 | 31 October 2026 |
| TypeScript SDK | 0.3.1 | 16 October 2026 |
| Python SDK | 0.3.1 | 16 October 2026 |
SDK parity
The two SDKs wrap the same REST API with the same scan methods and the same
ScanResult shape, but they're not perfectly symmetric yet:
- Live event stream (
subscribe()) is TypeScript-only today. - Automatic region-resolved gateway switching after authentication is
TypeScript-only — the Python client always talks to
base_url. - Retry/timeout tuning (
max_retries/timeout) is Python-only — the TypeScript client runs fixed retry defaults today. - Only Python has a same-repo integration for the OpenAI Agents SDK; only TypeScript has one for the Vercel AI SDK. Both scan tool results and tool calls from 0.3.0, and both fail open on scan errors by default.
AI-friendly
Every page is available as raw Markdown — append .md to any docs URL, or
use /llms.txt and /llms-full.txt to feed
the docs to an LLM.