Benefits
Specifications
How-to
Contact Us
Learn More
Introducing
•
TRU GUARD
Secure AI Code
From Day One
TruScan helps developers detect AI-specific security risks while building AI systems. Runs directly in your development workflow—catch issues early, fix faster.
End-to-End Coverage
Works Across your development workflow
One scanner, multiple integration points. Catch AI security issues wherever you work.
IDE Plugin
Real-time feedback as you code
Inline warnings with severity levels
Context-aware risk explanations
Suggested fixes and safer patterns
Scan on save or run manually
Pull Request Scanning
Catch risks before they merge
Automatic scans on every PR
Findings as review comments
Inline remediation guidance
Severity-based merge checks
CI/CD Friendly
Enforce security in automation
GitHub Actions, Jenkins, GitLab CI
Structured outputs (SARIF, JSON)
Configurable severity thresholds
Fail builds on critical risks
Open Source Values
AI Security should be transperant
04
No vendor lock-in
Use locally, in CI, or extend it for your stack. Self-host everything.
01
Free to use
No licenses, no usage limits, no paywalls. Download and use immediately.
02
Auditable by design
Understand exactly how detections work. View and customize all rules.
03
Community-driver
Built in the open, improved by contributors. Your voice shapes the roadmap.
Get started in minutes
Install, scan, and secure your AI code—no complex setup required
Quick Start
# Install from PyPI
$ pip install trusys-llm-scan
# Scan your project
$ trusys-llm-scan . --format console
# Generate SARIF for CI
$ trusys-llm-scan . --format sarif
--out results.sarif
Install IDE Extension
Get real-time scanning in VS Code or Visual Studio with inline warnings and fix suggestions
Add to Pull Requests
Automatically scan PRs with GitHub Actions—findings appear as review comments
Customize Rules
Extend with custom Semgrep rules for your framework-specific patterns
10+ frameworks
OpenAI, Anthropic, LangChain, FastMCP, LlamaIndex
50+ rules
Pre-built patterns for common AI vulnerabilities
3 output formats
Console, JSON, SARIF for every workflow
Start securing your AI code today
Join the community of developers building safer AI systems. Free, open source, and ready to use.
Trust & Security
Built for Enterprise Security Standard
Your AI evaluation infrastructure needs to be as secure and compliant as your production systems. TruEval is built with enterprise requirements in mind.
Enterprise-Grade Security
SOC 2 Type II certified. Your evaluation data is encrypted at rest and in transit.
Data Privacy First
Your prompts, datasets, and results stay in your environment. We never train on your data.
Global Compliance
GDPR, HIPAA, SOC 2 compliant. Built for regulated industries from day one.
Audit-Ready Documentation
Every evaluation is logged and versioned. Generate compliance reports on demand.
Flexible deployment options
Cloud-Hosted
Fully managed SaaS platform. Start evaluating in minutes.
On-Premise
Self-hosted in your data center. Maximum security and compliance.
Introducing
•
TRU GUARD
Secure AI Code
From Day One
TruScan helps developers detect AI-specific security risks while building AI systems. Runs directly in your development workflow—catch issues early, fix faster.
End-to-End Coverage
Works Across your development workflow
One scanner, multiple integration points. Catch AI security issues wherever you work.
IDE Plugin
Real-time feedback as you code
Inline warnings with severity levels
Context-aware risk explanations
Suggested fixes and safer patterns
Scan on save or run manually
Pull Request Scanning
Catch risks before they merge
Automatic scans on every PR
Findings as review comments
Inline remediation guidance
Severity-based merge checks
CI/CD Friendly
Enforce security in automation
GitHub Actions, Jenkins, GitLab CI
Structured outputs (SARIF, JSON)
Configurable severity thresholds
Fail builds on critical risks
Open Source Values
AI Security should be transperant
04
No vendor lock-in
Use locally, in CI, or extend it for your stack. Self-host everything.
01
Free to use
No licenses, no usage limits, no paywalls. Download and use immediately.
02
Auditable by design
Understand exactly how detections work. View and customize all rules.
03
Community-driver
Built in the open, improved by contributors. Your voice shapes the roadmap.
Get started in minutes
Install, scan, and secure your AI code—no complex setup required
Quick Start
# Install from PyPI
$ pip install trusys-llm-scan
# Scan your project
$ trusys-llm-scan . --format console
# Generate SARIF for CI
$ trusys-llm-scan . --format sarif
--out results.sarif
Install IDE Extension
Get real-time scanning in VS Code or Visual Studio with inline warnings and fix suggestions
Add to Pull Requests
Automatically scan PRs with GitHub Actions—findings appear as review comments
Customize Rules
Extend with custom Semgrep rules for your framework-specific patterns
10+ frameworks
OpenAI, Anthropic, LangChain, FastMCP, LlamaIndex
50+ rules
Pre-built patterns for common AI vulnerabilities
3 output formats
Console, JSON, SARIF for every workflow
Start securing your AI code today
Join the community of developers building safer AI systems. Free, open source, and ready to use.
Trust & Security
Built for Enterprise Security Standard
Your AI evaluation infrastructure needs to be as secure and compliant as your production systems. TruEval is built with enterprise requirements in mind.
Enterprise-Grade Security
SOC 2 Type II certified. Your evaluation data is encrypted at rest and in transit.
Data Privacy First
Your prompts, datasets, and results stay in your environment. We never train on your data.
Global Compliance
GDPR, HIPAA, SOC 2 compliant. Built for regulated industries from day one.
Audit-Ready Documentation
Every evaluation is logged and versioned. Generate compliance reports on demand.
Flexible deployment options
Cloud-Hosted
Fully managed SaaS platform. Start evaluating in minutes.
On-Premise
Self-hosted in your data center. Maximum security and compliance.