Skip to content

Home

Govern every AI call.
Finish every task.

Context Relay Protocol™ is the only runtime that gives your AI unbounded coherent context and enforced safety governance - with a single base_url change. No code rewrite. No model swap.

Start free in 60 seconds See pricing Explore the SDK
11.8xMore output
<50msSafety overhead
1 lineTo integrate
EU AI ActAudit-ready

What CRP solves

Context dies at 8 sections

Your model stops mid-task. Previous context is lost. There is no continuation.
CRP automatically continues across windows until the task is done.

No safety guardrails

Every AI call returns raw output. No risk score. No provenance. No audit trail.
CRP runs a 13-stage safety check on every call in under 50ms.

Compliance is manual

EU AI Act, ISO 42001, GDPR. You hire consultants for months.
CRP generates evidence packs automatically from runtime data.

Integration is expensive

Building context management, safety, and compliance from scratch takes quarters.
CRP is one line: base_url="https://gateway.crprotocol.io/v1"

Three products. One pipeline.

CRP Gateway

The runtime. Routes every AI call through governance + context management.

$29/mo

Developer tier - 10,000 calls/mo

Explore Gateway

CRP Comply

The compliance layer. Generates audit-ready deliverables from Gateway evidence.

$49/mo

Starter - 5,000 calls/mo · Annual $490

Explore Comply

CRP Scan

The scanner. Finds ungoverned AI calls in your codebase and opens remediation PRs.

Free

Public repos free · Private from $49/mo

Explore Scan

What's actually shipped

CRP is not a roadmap deck. These components are live, documented, and shipping today:

Python SDK

4 progressive levels from one-line governance to full infrastructure control.

  • Drop-in base_url proxy
  • crp.Client() with .complete() and .ask()
  • Document ingestion + source attribution
  • Tool registration + reasoning transparency
SDK Guide

CRP CLI

Command-line governance tools for scanning, validation, and benchmarking.

  • python -m crp scan -- find ungoverned AI calls
  • python -m crp validate -- config linting
  • python -m crp benchmark -- conformance suite
  • python -m crp audit -- export session trails
CLI Guide

GitHub Action

Auto-scan every PR for ungoverned AI calls with SARIF output.

  • Marketplace-published composite action
  • SARIF upload to Security tab
  • Auto-remediation PRs
  • VS Code extension (v0.2.0)
Scan Product

Gateway

OpenAI-compatible proxy with DPE, safety policy, and audit trails.

  • Self-host on Railway or Docker
  • 58 CRP headers on every call
  • HMAC-chained audit events
  • Redis-backed session store
Gateway Product

CRP Comply

Compliance platform with real-time dashboard and evidence packs.

  • EU AI Act Art. 6 risk classifier
  • Auto-generated DPIA + tech docs
  • Tamper-evident audit console
  • GitHub App for repo scanning
Comply Product

22 Specs

Open specifications defining every protocol layer.

  • Core protocol, headers, envelope
  • Continuation, DPE, safety policy
  • Session tokens, dispatch, CKF
  • Conformance, security, zero-CKF
Browse Specs

Who CRP is for

Developers

Ship governed AI in one line. Get context quality, safety scoring, and audit trails without building infrastructure.

Enterprises

EU AI Act, ISO 42001, GDPR compliance - auto-generated from real runtime evidence. SSO, data residency, private cloud.

CISOs & Compliance Officers

Real-time risk scoring, tamper-evident audit chains, and regulator-ready evidence packs. Not consultant PDFs.

AI Researchers

Compare strategies (CRP vs RAG vs Injection vs Hierarchical) with built-in benchmarking. Reproduce everything.

Startups

Free tier (100 calls/mo). Starter at $49/mo ($490/yr). Scale when you need SSO and data residency. No seat-based pricing.

Regulated Industries

Healthcare (HIPAA), finance (SOX), public sector. Air-gapped deployment, 7-year retention, signed DPA.

Read the full "Who is it for" breakdown

Before & After

❌ Without CRP

Task: "Write a 30-section K8s guide"
→ Output: 592 words, 8/30 sections
→ Truncated mid-sentence
→ No continuation
→ No quality score
→ Context lost between calls
→ No compliance evidence

✅ With CRP

Task: "Write a 30-section K8s guide"
→ Output: 6,993 words, 25/30 sections
→ Automatic multi-window continuation
→ Quality tier: A
→ Full provenance DAG
→ Knowledge persists in CKF
→ EU AI Act evidence generated

Same model. Same hardware. Same task. CRP produces 11.8x more content at identical throughput. The difference: CRP finishes the task - and proves it was safe.

Trusted by standards bodies

IETF submitted IANA submitted IEEE SA submitted ISO/IEC JTC 1/SC 42

Aligned with OWASP Top 10 (2025), ISO/IEC 42001:2023, EU AI Act (2024/1689), ISO/IEC 27001:2022, and NIST AI RMF.

Ready to govern your AI?
Start free. No credit card. 60-second setup.
Get Started Explore SDK