Organizational Intelligence
from Every AI Interaction

What if you could interview everyone in your organization every day and find out what they're actually doing? Corveil captures AI activity and turns it into intelligence you can act on.

Book a Demo →

Last updated

See What Your Organization Is Actually Doing

Corveil continuously analyzes AI activity and produces actionable intelligence — no surveys, no status meetings.

Activity Summaries

Hourly, daily, and weekly digests of what teams worked on. Know what happened without asking.

User Profiles

Auto-built profiles of expertise, projects, and focus areas. See who knows what across your org.

Recommendations

Actionable suggestions for cost optimization, productivity improvements, and security posture — generated from real usage patterns.

Knowledge Graph

Automatically maps relationships between people, projects, and technologies. Visual graph exploration and entity management.

Trend Detection

Surface emerging patterns in AI usage across teams. Spot shifts in tool adoption, model preferences, and workflow changes as they happen.

Cost Intelligence

Spending insights and optimization suggestions generated from real usage data. Know where budget is going and where it could go further.

Intelligence That Fits Your World

Secure AI for Government Environments

  • Zero-trust architecture — every request authenticated, every response logged
  • FIPS 140-2 compliant security headers and encryption standards
  • AWS GovCloud ready — deploy within your authorization boundary
  • Full audit logging — complete request/response capture for compliance
  • CUI-approved model routing — control which models handle sensitive data
  • Virtual API keys — provider credentials never exposed to end users
  • Knowledge graph — map organizational relationships and expertise across classified boundaries
  • Activity summaries — daily and weekly intelligence digests delivered automatically
  • Budget enforcement — per-user spend limits and alerts before overruns

AI Guardrails Your Security Team Controls

  • Guardrails pipeline — pre/post-call content filtering on every request
  • PII filtering — detect and redact sensitive data before it reaches providers
  • Jailbreak detection — block prompt injection and adversarial inputs
  • Content moderation — enforce acceptable use policies automatically
  • Budget enforcement — per-user and per-team spend limits with alerts
  • Incident-ready logging — full payloads for security investigation
  • Knowledge graph — visualize who works on what and surface hidden dependencies
  • Cost alerting — automatic warnings when request costs exceed thresholds
  • Webhook notifications — forward security events to your SIEM or alerting pipeline

One Endpoint, Every Model

  • OpenAI-compatible API — drop-in replacement, no SDK changes
  • 200+ models via OpenRouter, Vertex AI, and Bedrock from one endpoint
  • Multi-provider routing — switch models with a config change, not a refactor
  • Streaming support — real-time token streaming across all providers
  • Usage analytics — per-model cost tracking and request metrics
  • No vendor lock-in — your code stays clean, Corveil handles the plumbing
  • Knowledge graph — auto-map project dependencies, tech stack usage, and team expertise
  • Plugin SDK — extend Corveil with custom guardrails, connectors, and automations
  • Cost optimization — model-level spend insights and recommendations to reduce waste

The Plumbing That Powers the Intelligence

Corveil is a drop-in proxy for AI providers. Point your tools at Corveil and get visibility, control, and intelligence for free.

Virtual API Keys

Issue scoped keys to users and teams. Real provider credentials stay locked in your infrastructure — never exposed.

Spend Tracking & Budgets

Real-time cost tracking per user, team, and API key. Set hard budget limits and get alerts before overruns.

Request Logging & Audit

Full request/response capture with structured metadata. Built for compliance audits and incident investigation.

Guardrails & Content Filtering

Pre- and post-call filtering pipeline. PII detection, jailbreak prevention, and content moderation — inline, not bolted on.

Multi-Provider Routing

Access 200+ models through OpenRouter, Vertex AI, and Bedrock. One endpoint, zero provider lock-in.

OpenAI-Compatible API

Drop-in replacement for any OpenAI SDK client. Streaming, function calling, and tool use — all supported.

From AI Traffic to Organizational Intelligence

Deploy Corveil in front of your AI providers. Intelligence starts flowing immediately.

1

Connect

Point your AI clients at Corveil's OpenAI-compatible endpoint. Add your provider credentials once.

2

Control

Issue virtual API keys, set budgets, and configure guardrails. Define who can access which models.

3

Learn

The Insights Engine continuously analyzes activity and produces summaries, profiles, and recommendations. The Knowledge Graph maps relationships across people, projects, and technologies — so you know what's happening and how it all connects.

Deploy Corveil in Minutes

Choose the deployment method that fits your infrastructure.

Shell
helm upgrade --install corveil oci://ghcr.io/radiusmethod/citadel-helm/citadel-chart \
            --set citadel.environment=development \
            --set citadel.devLoginEnabled=true \
            --set providers.openrouter.apiKey="sk-or-xxx"

Requires Helm 3.x and a running Kubernetes cluster.

Shell
git clone https://github.com/radiusmethod/corveil-docker-compose.git
cd corveil-docker-compose
docker compose up -d

Starts Corveil, PostgreSQL, and Redis with sensible defaults.

Shell (macOS / Linux)
# Install the latest binary (downloads, verifies SHA-256 checksum, installs)
curl -sSL https://corveil.com/install.sh | sh

# Start in single-user mode
corveil --dev --openrouter-api-key sk-or-...

Single static binary for Linux and macOS. The installer automatically verifies the download against published SHA-256 checksums before installing. No containers or database setup required. Dashboard opens at localhost:8000. Manual downloads & checksums →

Shell
# Install the Corveil skill from ClawHub
openclaw skill install corveil

# Run the skill to start Corveil and configure routing
openclaw skill run corveil

Installs and runs Corveil via OpenClaw. The skill handles binary installation, startup, API key creation, and provider routing configuration automatically. OpenClaw setup guide →

Extend Corveil with Plugins & Templates

A growing ecosystem of guardrails, connectors, and workflow automations.

Guardrail Plugins

PII redaction, jailbreak detection, content moderation, and more — plug in the safety layers you need.

6 Built-in

Model Connectors

OpenRouter, Vertex AI, Bedrock, and Azure OpenAI. Connect to any provider through a unified interface.

4 Available

Workflow Templates

Pre-built automations for cost alerting, webhook notifications, and approval gates.

3 Templates

Connects to Your Entire Stack

SDKs, infrastructure tools, and security platforms — all supported out of the box.

Developer & API

  • Python SDK
  • Node.js SDK
  • REST API
  • Webhooks
  • Claude Code
  • OpenClaw

Infrastructure

  • Kubernetes & Helm
  • CI/CD Pipelines
  • SIEM Forwarding
  • SSO / OIDC

Frequently Asked Questions

What is Corveil?

Corveil is an organizational intelligence platform that acts as a zero-trust AI gateway. It routes LLM requests through a single secure endpoint while capturing knowledge about how your organization uses AI — building a knowledge graph of people, projects, technologies, and decisions.

Is Corveil free?

Yes. Corveil is free to download and run. The binary ships as a single static executable with no external dependencies. Just run "corveil --dev" and you have a fully functional gateway with a built-in SQLite database, admin dashboard, and all features enabled.

Does Corveil work with Claude Code?

Yes. Claude Code connects to Corveil by setting ANTHROPIC_BASE_URL to your Corveil instance. Corveil supports both Direct mode (Corveil provides the API key) and Passthrough mode (Claude Code Max users route through Corveil for logging and guardrails while using their own subscription).

What is organizational intelligence?

Organizational intelligence is the understanding of who knows what, who works on what, and how your organization actually operates. Corveil builds this automatically by analyzing AI activity — extracting entities like people, projects, and technologies from conversations and mapping the relationships between them into a searchable knowledge graph.

What LLM providers does Corveil support?

Corveil supports Anthropic (Claude), OpenRouter (200+ models including GPT-4, Llama, Mistral), Google Vertex AI (Gemini), and AWS Bedrock (including GovCloud). All providers are accessed through a single OpenAI-compatible API endpoint.

Does Corveil support self-hosted deployments?

Yes. Corveil is designed for self-hosted deployment. It ships as a single Go binary that runs anywhere — bare metal, Docker, Kubernetes (via Helm chart), or cloud platforms like AWS GovCloud. Your data never leaves your infrastructure.

How is Corveil different from other AI gateways?

Most AI gateways are proxies — they route traffic and log requests. Corveil does that too, but it also builds organizational intelligence: a knowledge graph that maps relationships across people, projects, and technologies, plus an insights engine that produces daily and weekly activity summaries. It is the difference between a proxy and a platform.