Skip to content
SPECIFICTION
Get listed

LLM Guard

github.com

Free plan LinuxAPISelf-hosted
Visit github.com
Spec score 7.6 #11 of 31 in LLM Security Tools

What it is

LLM Guard is a self-hosted security toolkit for checking interactions with large language models. It scans prompts and outputs for concerns such as prompt injection, secrets, personally identifiable information, toxicity, bias, malicious URLs, and factual consistency. It can sanitize interactions, detect harmful language, help prevent data leakage, and resist prompt injection attacks. The documentation includes examples for the OpenAI SDK, LangChain, LiteLLM, and LlamaIndex. In the OpenAI examples, prompts and responses are scanned; a streaming example also checks response chunks. LLM Guard can run as an API, and custom scanners can be added. Installation uses `pip install llm-guard` and requires Python 3.9 or higher. It is free and listed under the MIT License, with API, Linux, and self-hosted platforms. The repository was archived on July 9, 2026, is read-only, and is no longer actively developed or maintained. Production deployment assistance is directed to GitHub issues, Slack, and [email protected].

Spec sheet

Purpose
LLM Guard is a security toolkit for LLM interactions that sanitizes inputs, detects harmful language, helps prevent data leakage, and resists prompt injection attacks.Read 9 Oct 2026 · github.com
Intended users
The project describes production deployment and offers tutorials for developers building LLM applications, including guarded RAG and agent workflows.Read 9 Oct 2026 · github.com
Integrations
The documentation includes integrations and examples for the OpenAI SDK, LangChain, LiteLLM, and LlamaIndex.Read 9 Oct 2026 · protectai.github.io
Support
The README directs users to GitHub issues, Slack, and [email protected] for production deployment assistance.Read 9 Oct 2026 · github.com
License
The GitHub repository lists the project under the MIT License.Read 9 Oct 2026 · github.com
API deployment
The documentation provides a deployment option to run LLM Guard as an API.Read 9 Oct 2026 · protectai.github.io
Customization
The documentation describes adding custom scanners to LLM Guard.Read 9 Oct 2026 · protectai.github.io
Input and output scanners
It provides scanners for prompts and outputs, including anonymization, prompt injection, secrets, toxicity, bias, malicious URLs, and factual consistency.Read 9 Oct 2026 · github.com
Installation
The project documents installation with `pip install llm-guard` and requires Python 3.9 or higher.Read 9 Oct 2026 · protectai.github.io
Maintenance status
GitHub says the repository was archived on July 9, 2026, is read-only, and is no longer under active development or maintenance.Read 9 Oct 2026 · github.com
OpenAI request handling
The OpenAI SDK example scans prompts before sending requests and scans responses; its streaming example scans prompts alongside the API request and checks response chunks.Read 9 Oct 2026 · protectai.github.io
Security coverage
The project says it can sanitize interactions, detect harmful language, prevent data leakage, and resist prompt injection attacks.Read 9 Oct 2026 · protectai.github.io

Plans and prices

LLM Guard Free Open source solution · repository archived and no longer actively developed or maintained Read 9 Oct 2026 · github.com

Every LLM Guard plan and price →

Strong points and limits

Strong points

  • Scans both prompts and model outputs.
  • Includes scanners for injection, secrets, toxicity, and bias.
  • Integrates with OpenAI SDK, LangChain, LiteLLM, and LlamaIndex.
  • Can run as an API and accept custom scanners.
  • Free, MIT-licensed, and self-hosted.

Limits

  • Repository is archived and read-only.
  • Requires Python 3.9 or higher.
  • Self-hosted deployment requires managing the environment.

Who it suits

It suits developers building LLM applications, including guarded RAG and agent workflows, who can manage a self-hosted tool. Its archived status matters to teams assessing ongoing maintenance.

Verdict

LLM Guard brings prompt and output scanning, integrations, API deployment, and custom scanner support into a free toolkit. Its archived, unmaintained repository is an important consideration for production use.

Where Specifiction places it

Alternatives to LLM GuardAll alternatives →