Core Engine

Detection & Classification

Two-tier analysis: instant rule-based detection, plus optional deep analysis for richer context.

🔍

Rule-Based Classifier

Deterministic breach detection in <1ms. No LLM in the critical path. Pattern matching for PII (SSN, Aadhaar, PAN), PHI, card data, financial hallucinations, and 40+ violation types across four verticals.

🧠

Agentic Deep Analysis

Optional async LangGraph pipeline powered by Claude. A six-node analysis graph adds rationale, regulatory mapping, severity justification, and remediation guidance — without blocking the agent.

Integrity

Tamper-evident logging

Every record is cryptographically chained. If a single entry is altered, the chain breaks.

🔗

SHA-256 Hash Chain

Every breach record is checksummed. Each record includes the hash of the previous record, creating an immutable chain. Integrity scanning runs every 6 hours automatically.

📝

Immutable Dual-Write

Every breach writes simultaneously to PostgreSQL/SQLite AND real-time JSONL files on disk. Two independent, auditable trails. Ship JSONL to your SIEM.

🔒

Tamper Alerts

When the integrity scanner detects a broken hash chain, it creates a tamper_alert record and fires a CRITICAL webhook. You know immediately if someone touched the logs.

Zero-Touch

Auto-instrumentation

Your agent code stays untouched. The policy agent hooks into Python's import system and patches all supported frameworks automatically.

Supported frameworks

OpenAI Anthropic LangChain OpenClaw

How it works

  1. breach-intel install-hook writes a persistent sitecustomize.py
  2. When any Python process starts, the hook runs first
  3. It checks for BREACH_INTEL_URL env var
  4. If set, patches all detected AI framework methods
  5. Agent auto-registers with the policy agent
  6. Every LLM response → POST /events (5s timeout, silent on failure)
$ breach-intel doctor BREACH_INTEL_URL = http://localhost:8080 Persistent hook installed Detected frameworks: OpenAI, Anthropic Server health: OK (v0.3.1) Credentials: valid ───────────────────────────── All checks passed.
Operations

Production-grade infrastructure

📊

Live Dashboard

Single-file React SPA at /dashboard. Breach counts by severity, agent heatmaps, live feed with click-to-inspect, and vertical distribution.

🚨

Webhook Alerts

CRITICAL breaches fire instantly to Slack, Discord, or generic webhooks. Configure thresholds and routing per vertical and severity.

🏗️

Auto-Scaling

When event load exceeds 500/min (configurable), additional policy agent instances spawn via Docker, K8s, or subprocess.

🔐

Multi-Tenant Auth

Scoped API keys with tenant isolation. Rate limiting at 300 events/min per key. Admin keys exempt. Full RBAC for compliance teams.

📈

Prometheus Metrics

Built-in /metrics endpoint for Grafana integration. Track event throughput, breach rates, classifier latency, and spawn counts.

🗄️

Retention & Archival

Automated retention policies with integrity scanning every 6 hours. Old records archived with full hash chain verification.

Industry Coverage

Purpose-built for regulated industries

Each vertical has its own breach taxonomy mapped to the specific regulations your compliance team cares about.

🏦

Fintech

Production Ready

12 breach types — PII exposure, card data, cross-tenant leaks, unauthorized financial advice, suspicious transactions, privilege escalation.

SOC 2GDPRCCPAPCI-DSSSOXSEBIRBIFINCEN
🏥

Healthcare

Beta

14 breach types — PHI exposure, clinical notes, unauthorized prescriptions, diagnostic hallucinations, minors data, mental health, genomic data.

HIPAA42 CFR Part 2GDPRDPDPHL7/FHIR
💊

Pharma

Beta

14 breach types — trial data fabrication, unblinding, 21-CFR-11 audit trail violations, e-signature bypass, pharmacovigilance, GMP violations.

FDA 21-CFR-11ICH-E6ICH-Q10EMAGDPR

Sports

Planned

Odds manipulation detection, insider data leaks, athlete PII protection, match-fixing signal analysis.

Coming Soon

See it in action

Request early access and we'll set up a live demo with your stack.

Request Early Access