Does Complior send my code to the cloud?
Does Complior send my code to the cloud?
No. The base scan (L1–L4) runs entirely offline with zero network calls. L5 (LLM analysis) and eval are opt-in and only send specific findings or probes — never your full codebase. You control which LLM provider to use and supply your own API key.
Do I need an account to use Complior?
Do I need an account to use Complior?
No. The open-source CLI, TUI, SDK, and MCP server require no account. The optional SaaS dashboard (fleet management, team collaboration) requires a subscription.
What languages does Complior support?
What languages does Complior support?
Scan works with TypeScript/JavaScript, Python, Go, Rust, and Java. The scanner detects 57+ AI frameworks across these languages. Eval works with any HTTP endpoint regardless of language.
Does the LLM make compliance decisions?
Does the LLM make compliance decisions?
Never. All compliance checks (L1–L4) are deterministic — AST patterns and rules. LLM (L5) only clarifies findings in the uncertain zone (50–80% confidence). The LLM cannot override, approve, or reject a compliance check.
Can I use Complior in CI/CD?
Can I use Complior in CI/CD?
Yes. Use
complior scan --ci --threshold 70 --fail-on critical to gate deployments. Supports JSON and SARIF output for GitHub Code Scanning, GitLab, and other CI systems.Is the EU AI Act relevant to me if I'm outside the EU?
Is the EU AI Act relevant to me if I'm outside the EU?
Yes, if your users are in the EU. The Act applies to providers and deployers whose AI systems affect EU residents, regardless of company location — similar to GDPR.
What's the difference between scan and eval?
What's the difference between scan and eval?
Scan = static code analysis (offline, 2–5 seconds). Examines your source code, configs, and docs.Eval = dynamic system testing (online, sends 680 probes to a live endpoint). Tests actual AI behavior for bias, transparency, and security.See Scan vs Eval for a detailed comparison.
How is the compliance score calculated?
How is the compliance score calculated?
The score (0–100) is a weighted combination across layers: L1 (1.0), L2 (0.95), L3 (0.90), L4 (0.75), L5 (0.70). Critical violations cap the maximum achievable score. See Scoring for details.
Can I customize which rules run?
Can I customize which rules run?
Yes. Use
project.toml to configure scan scope, exclude files, and select frameworks. Use --agent <NAME> to scan specific AI systems only.What is an Agent Passport?
What is an Agent Passport?
A standardized identity card for an AI system — 36 fields covering name, risk class, autonomy level, permissions, compliance status, and more. Ed25519 signed for tamper-proof integrity. See Agent Passport.
How do I integrate with Claude Code / Cursor / Windsurf?
How do I integrate with Claude Code / Cursor / Windsurf?
Complior exposes an MCP server with 8 tools. Your AI coding agent connects via MCP and can scan, fix, and query compliance status directly. See MCP Server.
Is Complior free?
Is Complior free?
The open-source CLI (daemon + TUI + SDK + MCP server) is free and AGPLv3 licensed. The SaaS dashboard for fleet management and team collaboration is paid (Growth €149/mo, Enterprise €499/mo).
What happens if I don't comply by August 2, 2026?
What happens if I don't comply by August 2, 2026?
Fines up to €35M or 7% of global annual revenue (whichever is higher) for prohibited practices, and up to €15M or 3% for other violations. National authorities enforce within each EU member state.
Can I export compliance data for auditors?
Can I export compliance data for auditors?
Yes.
complior agent audit-package creates a tar.gz bundle with passports, evidence chain, scan results, FRIA, and all compliance documents — ready for regulator review.