# Complior

## Docs

- [Agent & Passport Endpoints](https://docs.complior.ai/api/agent.md): Passport lifecycle, FRIA generation, evidence chain, export, audit trail, and document generation.
- [Eval Endpoints](https://docs.complior.ai/api/eval.md): Dynamic system evaluation — 680 probes for bias, transparency, security, and conformity testing.
- [Fix Endpoints](https://docs.complior.ai/api/fix.md): Preview, apply, and undo compliance fixes. Batch operations with validation.
- [API Reference](https://docs.complior.ai/api/overview.md): Complior engine exposes a REST API on localhost for CLI, TUI, and MCP integrations. 100+ endpoints across scan, eval, fix, agent, and system operations.
- [Scan & Eval Endpoints](https://docs.complior.ai/api/scan.md): Static analysis, deep scan, diff, SBOM, and dynamic evaluation endpoints.
- [System Endpoints](https://docs.complior.ai/api/status.md): Engine status, events, file operations, onboarding, badges, sharing, sync, and more.
- [Changelog](https://docs.complior.ai/changelog.md): Release history and notable changes for Complior.
- [complior agent](https://docs.complior.ai/cli/agent.md): Agent Passport lifecycle — init, list, show, validate, export, FRIA, evidence, and more.
- [CLI Reference](https://docs.complior.ai/cli/commands.md): Complete command reference for the complior CLI. 40+ commands with flags and examples.
- [Configuration](https://docs.complior.ai/cli/config.md): Configuration files, environment variables, and project setup.
- [complior daemon](https://docs.complior.ai/cli/daemon.md): Background daemon management — start, stop, and status.
- [complior eval](https://docs.complior.ai/cli/eval.md): Dynamic evaluation of live AI systems — 680 probes across bias, transparency, security, and conformity.
- [complior fix](https://docs.complior.ai/cli/fix.md): Auto-remediate compliance findings — preview, apply, and undo fixes.
- [complior scan](https://docs.complior.ai/cli/scan.md): 5-layer static compliance analysis with multiple output formats and CI integration.
- [AI Usage Policy](https://docs.complior.ai/compliance-docs/ai-policy.md): Industry-specific AI usage policy templates — HR, Finance, Healthcare, Education, Legal.
- [Audit Package](https://docs.complior.ai/compliance-docs/audit-package.md): Complete ZIP archive for the regulator — passports, evidence, documents, scores.
- [FRIA](https://docs.complior.ai/compliance-docs/fria.md): Fundamental Rights Impact Assessment — required by Art.27 for all high-risk AI systems.
- [Compliance Documents](https://docs.complior.ai/compliance-docs/overview.md): 6 document types Complior generates — FRIA, AI Policy, Worker Notification, and more.
- [Conformity Tests](https://docs.complior.ai/eval/conformity-tests.md): 11 EU AI Act categories covering transparency, bias, oversight, and more. 168 deterministic + 212 LLM-judged = 380 conformity tests, plus 300 security probes.
- [Eval Modes](https://docs.complior.ai/eval/eval-modes.md): 4 composable eval modes — deterministic, LLM-judged, security probes, and full.
- [Eval vs Scan](https://docs.complior.ai/eval/eval-vs-scan.md): When to use scan (static analysis) vs eval (dynamic testing) — and why you need both.
- [Eval Overview](https://docs.complior.ai/eval/overview.md): Dynamic AI system testing — 680 probes against live endpoints. Tests actual behavior, not just code.
- [Security Probes](https://docs.complior.ai/eval/security-probes.md): 300 attack probes based on OWASP LLM Top 10 and MITRE ATLAS.
- [Document Generation](https://docs.complior.ai/fix/document-generation.md): 14 EU AI Act document templates, pre-filled from Agent Passport data.
- [Fix Strategies](https://docs.complior.ai/fix/fix-strategies.md): 17 strategies across 5 categories: Code, Docs, Config, Dependencies, Passport.
- [LLM Enrichment](https://docs.complior.ai/fix/llm-enrichment.md): Use --ai flag to have LLM fill document placeholders. Safe, proxied, and optional.
- [Fix Overview](https://docs.complior.ai/fix/overview.md): Deterministic auto-remediation engine — 17 strategies across code, docs, config, deps, and passport.
- [Your First Auto-Fix](https://docs.complior.ai/getting-started/first-fix.md): Auto-remediate compliance issues with strategies across code, docs, config, and dependencies.
- [Your First Agent Passport](https://docs.complior.ai/getting-started/first-passport.md): Generate a standardized AI system identity card — 36 fields, ed25519 signed, 65–70% auto-filled from code.
- [Your First Scan](https://docs.complior.ai/getting-started/first-scan.md): Understand what complior scan does, how the layers work, and what the output means.
- [Quick Start](https://docs.complior.ai/getting-started/quickstart.md): 4 commands from zero to audit-ready compliance artifacts.
- [What's New](https://docs.complior.ai/getting-started/whats-new.md): Latest changes in Complior — v1.0.1 patch + v1.0.0 GA release notes.
- [EU AI Act in 5 Minutes](https://docs.complior.ai/guides/compliance-101.md): A developer's guide to the EU AI Act — what it is, who it affects, and what you need to do.
- [FAQ](https://docs.complior.ai/guides/faq.md): Frequently asked questions about Complior.
- [Glossary](https://docs.complior.ai/guides/glossary.md): Key terms and concepts used in Complior and EU AI Act compliance.
- [Troubleshooting](https://docs.complior.ai/guides/troubleshooting.md): Common issues and solutions when using Complior.
- [Introduction](https://docs.complior.ai/index.md): Complior — open-source AI compliance platform for EU AI Act. Scan code, test AI systems, auto-fix issues, generate documents, and create audit-ready Agent Passports.
- [Installation](https://docs.complior.ai/installation.md): Install Complior CLI — npx, npm, curl, or cargo.
- [MCP Server](https://docs.complior.ai/mcp/overview.md): Compliance tools for AI agents via Model Context Protocol. 7 tools for Claude Code, Cursor, Windsurf.
- [MCP Setup](https://docs.complior.ai/mcp/setup.md): Configure Complior as MCP server for Claude Code, Cursor, Windsurf, and other agents.
- [MCP Tools Reference](https://docs.complior.ai/mcp/tools-reference.md): Full input/output schema for all 13 Complior MCP tools.
- [Autonomy Levels](https://docs.complior.ai/passport/autonomy-levels.md): 5-level autonomy scale with automatic AST detection.
- [Data Pipeline](https://docs.complior.ai/passport/data-pipeline.md): 11 stages from 0% to 100%+ passport completeness — init through production monitoring.
- [Endpoint Detection](https://docs.complior.ai/passport/endpoints.md): How Complior discovers and manages AI system endpoints in passports — automatic detection from code, Docker, .env, plus manual configuration.
- [Evidence Chain](https://docs.complior.ai/passport/evidence-chain.md): Tamper-proof cryptographic chain: SHA-256 hash → ed25519 signature → chain.
- [Export Formats](https://docs.complior.ai/passport/export-formats.md): Export passports to A2A, AIUC-1, and NIST AI RMF formats.
- [Agent Passport](https://docs.complior.ai/passport/overview.md): Standardized AI system identity card — 36 fields, ed25519 signed, 2 generation modes.
- [Passport Modes](https://docs.complior.ai/passport/passport-modes.md): Two ways to generate a passport: Auto (from code) and Runtime (from observation).
- [Risk Classification](https://docs.complior.ai/passport/risk-classification.md): Dual-source risk classification: autonomy level × project domain.
- [CI/CD Integration](https://docs.complior.ai/scan/ci-cd.md): Add compliance gates to your CI/CD pipeline with threshold checks and structured output.
- [Scan Overview](https://docs.complior.ai/scan/overview.md): 5-layer deterministic static analysis engine. Scans your codebase for EU AI Act compliance gaps in 2–5 seconds.
- [Scan Tiers](https://docs.complior.ai/scan/scan-tiers.md): 6 composable scan tiers — from zero-dependency offline to full cloud enrichment.
- [Scoring](https://docs.complior.ai/scan/scoring.md): Dual scoring system — compliance + security — across multiple international frameworks.
- [Advanced Features](https://docs.complior.ai/sdk/advanced.md): Config hot-reload, retry with backoff, streaming support, interaction logging, provider detection, and proxy architecture.
- [Agent Mode](https://docs.complior.ai/sdk/agent-mode.md): compliorAgent() — passport-enforced compliance with permission control, rate limiting, budget tracking, circuit breaker, and action logging.
- [Bias Detection](https://docs.complior.ai/sdk/bias-detection.md): Screen LLM responses for bias across 15 EU Charter Art.21 protected characteristics with domain-aware scoring.
- [Configuration Reference](https://docs.complior.ai/sdk/configuration.md): Complete reference for MiddlewareConfig, AgentConfig, and TOML file-based configuration.
- [Error Handling](https://docs.complior.ai/sdk/errors.md): 12 error classes for compliance violations — catch specific errors with instanceof.
- [Hooks Reference](https://docs.complior.ai/sdk/hooks.md): 6 pre-hooks and 8 post-hooks — what each one does and how to configure it.
- [HTTP Middleware](https://docs.complior.ai/sdk/middleware.md): 4 HTTP middleware adapters (Express, Fastify, Hono, Next.js) that inject compliance headers from SDK responses.
- [SDK Overview](https://docs.complior.ai/sdk/overview.md): @complior/sdk — runtime compliance wrapper for LLM clients. 14 hooks, 4 providers, zero config.
- [PII Detection & Redaction](https://docs.complior.ai/sdk/pii-detection.md): 50+ PII types across 6 categories with checksum validators. EU-focused: IBAN, BSN, NIR, PESEL, Codice Fiscale, and GDPR Art.9 special categories.
- [Providers](https://docs.complior.ai/sdk/providers.md): 4 supported LLM providers: OpenAI, Anthropic, Google, Vercel AI SDK.
- [SDK Quick Start](https://docs.complior.ai/sdk/quick-start.md): Add compliance protection to your LLM calls in 3 lines of code.
- [Safety Filter & HITL Gate](https://docs.complior.ai/sdk/safety.md): 5-category safety pattern scanning and Human-in-the-Loop gate with 4 built-in rules (Art.14/Art.15).
- [EU AI Act](https://docs.complior.ai/standards/eu-ai-act.md): 108 deployer obligations mapped to Complior features. Coverage: ~50% automated, ~35% templates, ~15% manual.
- [Other Frameworks](https://docs.complior.ai/standards/frameworks.md): OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF — security and risk frameworks.
- [ISO 42001](https://docs.complior.ai/standards/iso-42001.md): 39 Annex A controls mapped to Complior. Current coverage: ~45–50%.

## OpenAPI Specs

- [openapi](https://docs.complior.ai/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/complior/complior)