GovrixGovrix
EU AI ACT: UP TO €35M PENALTY · AUGUST 2026

Your AI agents are running.
Nobody knows what they're doing.

See every token your agents spend, block the ones that go rogue, and hand your auditor a tamper-proof log — without changing a single line of code.

<5msp99 latency
0code changes to install
MITopen source

Works with your stack —

OpenAIAnthropicAWS BedrockLangChainCrewAIAutoGen
Scroll

LIVE DASHBOARD

See everything your agents do. In real time.

localhost:3000/dashboard
LIVE
Active Agents
4/5
Total Calls (24h)
6,602
Cost Today$
$810
PII Alerts
10 flagged
Agent Registry5 agents
AgentStatusModelCallsCostPII
billing-agent
active
gpt-4o1,842$142.80
support-agent
active
claude-3.53,291$389.40
7
research-bot
active
gpt-4o-mini892$67.20
sales-copilot
blocked
gpt-4o421$198.10
3
report-agent
active
claude-3.5156$12.40
Cost (7d)↗ 12%
Daily budget$810 / $1,000
By model
gpt-4o54%
claude-3.532%
gpt-4o-mini14%
Event FeedLIVE
audit trail active

Real dashboard from Govrix Scout. Every agent call tracked, every dollar attributed, every PII instance flagged.

OpenAI compatible
Anthropic Claude
AWS Bedrock
Azure OpenAI
Google Gemini
Cohere
Mistral
LiteLLM
Ollama
Any OpenAI-compatible API
OpenAI compatible
Anthropic Claude
AWS Bedrock
Azure OpenAI
Google Gemini
Cohere
Mistral
LiteLLM
Ollama
Any OpenAI-compatible API

The Problem

Your CFO just asked why the OpenAI bill tripled this month.

You can't answer. Nobody can. Your agents are spending money you can't see, leaking data you can't detect, and making decisions you can't audit. Here's what your production logs actually look like right now.

your-production-agents · ungoverned · no audit trail
LIVE
💸

$47K bill from one agent

A single runaway agent loop burned $47K in one night. No alert. No cap. Nobody noticed until the invoice.

🔓

PII leaked to LLM providers

Customer SSNs, emails, phone numbers flowing to OpenAI in plain text. No detection. No masking. No audit trail.

👻

Shadow agents everywhere

Engineering shipped 12 agents. You know about 4. The other 8 are calling GPT-4 with production data right now.

⚖️

EU AI Act — August 2026

€35M in penalties for non-compliant AI systems. Your agents need tamper-proof audit logs. Today they have none.

Sound familiar? This is what Govrix fixes. ↓

THE FIX

One env var. Instant visibility.

Set one environment variable. Scout intercepts every agent call — tracking costs, catching failures, flagging PII. No code changes. No SDKs. No friction.

  • Per-agent cost tracking from first request
  • Works with OpenAI, Anthropic, Bedrock, and more
  • Auto-discovery — agents appear in dashboard instantly
See per-agent costs
Open Source · MITSelf-hosted in 5 minNo credit card
.env · shell
ACTIVE

Added latency: <5ms. Your agent doesn't notice.

Get Scout Free — no credit card

Open source · MIT licensed · Self-hosted in 2 minutes

<1msP50 proxy latency
<30sto add governance to any agent
<5msP99 proxy latency
100%self-hosted · data never leaves your infra

HOW IT WORKS

From zero to governed in minutes

No SDK to install. No agent code to change. Just point and govern.

01

Deploy

Docker image or single binary. No SDK, no code changes, no dependencies.

$ docker pull govrix/scout:latest
$ docker run -p 4000:4000 govrix/scout
✓ Proxy → 0.0.0.0:4000
✓ Mgmt API → :4001
<5 min setupSingle binaryMIT licensed
02

Point

Set one env var. All agent traffic routes through Govrix — zero code changes.

export OPENAI_BASE_URL="https://localhost:4000/v1"
# Your agents now run through Govrix
✓ 3 agents discovered automatically
OpenAI compat.AnthropicAny provider
03

See Everything

Agents appear instantly. Track costs, detect PII, enforce budgets, generate audit logs.

govrix · dashboard
AgentCallsCost
billing-agent
142
$0.042
support-agent
381
$0.118PII
report-agent
27
$0.009
PII detectionBudget capsAudit logs
Step 02

Point

2 / 3

CAPABILITIES

Everything you need. Nothing you build.

v1 is live and open source — full observability, cost tracking, PII detection, and audit trails. v2 brings managed cloud, multi-provider routing, identity, and compliance reports.

v1 — Live & Open Source
v1 · Live

Cost Attribution

Know where every AI dollar goes

Per-agent, per-model, per-day cost breakdown. Catch $47K runaway loops before your CFO does.

v1 · Live

Agent Discovery

See every agent. Automatically.

No registration, no SDK. Agents appear in the dashboard the moment they route through the proxy.

v1 · Live

PII Detection

Flag sensitive data in real time

SSN, credit cards, emails, phone numbers, addresses — detected inline with <0.5ms overhead. 25+ pattern tests.

v1 · Live

Tamper-Proof Audit

SHA-256 Merkle lineage chain

Every event gets a cryptographic hash. Immutable, compliance-ready evidence your auditor will actually accept.

v1 · Live

Protocol Native Streaming

True SSE pass-through

Works with OpenAI, Anthropic, and any compatible endpoint. No buffering. <5ms p99 added latency.

v1 · Live

Fail-Open Design

Governance never blocks production

Proxy is stateless and fail-open. If Govrix goes down, agents keep working. Kill switch for individual agents when needed.

v2 — Coming Soon · Join the Waitlist
v2 · Coming Soon

Multi-Provider Routing

Route across any provider

Bedrock, Azure OpenAI, VertexAI, Cohere — load balance, failover, and route by policy. One endpoint for all models.

v2 · Coming Soon

SSO / OIDC + RBAC

Identity without the SSO tax

OIDC authentication, role-based access control, team-scoped permissions. No $500/seat SSO upgrade fee.

v2 · Coming Soon

Webhook Connectors

Push events everywhere

Datadog, Splunk, PagerDuty, custom webhooks. Real-time alerts when budgets break or PII is detected.

v2 · Coming Soon

Compliance Reports

Audit-ready out of the box

One-click SOC 2, EU AI Act, HIPAA, and FINRA compliance reports. Evidence packages your auditor will accept.

v2 · Coming Soon

Real-Time PII Masking

Redact before it leaves

Mask sensitive data in-flight before it reaches upstream APIs. Emails, SSNs, credit cards redacted at the proxy layer.

v2 · Coming Soon

A2A Identity & mTLS

Agent certificates and permissions

Issue certificates per agent, scope permissions via mTLS, and enforce agent-to-agent trust boundaries.

v1 is free forever. v2 launches when your auditor asks.

ROADMAP

v1 is live. v2 is coming.

v1 — Live Now · Free Forever

Scout v1

Open source. Self-hosted. Production-ready. Apache 2.0 licensed.

  • Transparent proxy (no code changes)
  • Agent auto-discovery
  • Full request / response logging
  • Cost tracking & attribution
  • PII detection (5 types)
  • YAML policy engine
  • Tamper-proof audit trail (SHA-256 Merkle chain)
  • Budget enforcement (daily/monthly limits)
  • Session & trace tracking
  • 18-page real-time dashboard
  • Docker + Kubernetes deployment
  • Community support
v2 — Coming Soon

Scout v2

Managed cloud. Compliance automation. Multi-provider routing. Join the waitlist for early access.

  • Everything in v1, plus:
  • Multi-provider routing (Bedrock, Azure, Vertex)
  • SSO / OIDC + role-based access control
  • Real-time PII masking (redact before upstream)
  • Webhook connectors (Datadog, Splunk, PagerDuty)
  • One-click compliance reports (SOC 2, EU AI Act, HIPAA)
  • A2A identity & mTLS agent certificates
  • Managed cloud with SLA
  • On-prem / VPC deployment option
  • Dedicated support

Start with v1 today. Get early access to v2 when it launches.

COMPLIANCE DEADLINE

The EU AI Act enforcement deadline is real.

August 2, 2026. Up to €35M or 3% of global revenue for non-compliant AI systems. Scout gives you a tamper-proof audit trail today — for free.

132
Days
21
Hours
51
Minutes
01
Seconds

EU AI Act

Up to €35M in penalties or 3% of global revenue for non-compliant AI systems.

SOC 2

Audit trails and access logs are mandatory for enterprise AI deployments.

HIPAA

PHI in AI agent outputs requires complete, tamper-proof audit trails.

FAQ

Frequently asked questions

WHY THIS MATTERS

Real problems. Real stakes.

Cost OverrunSaaS / Engineering
Wewokeuptoa$47KbillbecauseoneagentgotstuckinaloopcallingGPT-4allnight.Noalertfired.Nobodyknewuntilfinancepingedus.

Based on real incidents reported across AI engineering teams

How Govrix solves this

Govrix tracks per-agent, per-model cost in real time. Set a budget cap — when it hits, the agent stops. No more surprise invoices.

Real-world example

OpenAI's own documentation warns about runaway token usage. Federico Viticci reported burning 180M+ tokens ($3,600/month) using Claude with Apple Shortcuts — with zero cost controls in place.

Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022Cost Overrun • PII Leakage • Compliance Gap \u2022

Built for teams in —

FintechHealthtechSaaSE-CommerceRegulated Industries
Your Agents. Right Now.

Your agents are bleeding money right now.

See where — in 2 minutes.

Free, open-source proxy. MIT licensed. Self-hosted in 2 minutes. No credit card.

Takes 30 seconds · No credit card · MIT licensed

<5ms added latency
MIT license
Self-hosted in 2 min