Skip to content

docs: add ADOPTERS.md and make deployment guides multi-cloud #1040

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Imran Siddique (imran-siddique) merged 1 commit into from
Apr 15, 2026
Merged

docs: add ADOPTERS.md and make deployment guides multi-cloud #1040

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 56 additions & 0 deletions ADOPTERS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
# Adopters

Organizations using the Agent Governance Toolkit in production or evaluation.

_If your organization uses AGT, please add it here! It helps the project gain
momentum and credibility. Submit a PR editing this file — see
[CONTRIBUTING.md](CONTRIBUTING.md) for guidelines._

## Production

| Organization | Industry | Use Case | Contact |
|---|---|---|---|
| | | | |

## Evaluation / Pilot

| Organization | Industry | Use Case | Contact |
|---|---|---|---|
| | | | |

## Academic / Research

| Organization | Focus Area | Contact |
|---|---|---|
| | | |

---

## How to Add Your Organization

1. Fork the repository
2. Edit this file — add a row to the appropriate table
3. Submit a pull request

**What to include:**
- **Organization:** Your company/institution name (link to website)
- **Industry:** e.g., Financial Services, Healthcare, Technology, Government
- **Use Case:** Brief description (1-2 sentences) of how you use AGT
- **Contact:** GitHub handle of a representative (optional but helpful)

**Example:**

```markdown
| [Contoso](https://contoso.com) | Financial Services | Policy enforcement for trading agents — deterministic action governance on multi-agent workflows processing market data | [@jsmith](https://github.com/jsmith) |
```

We welcome all adopters — from "just evaluating" to "running in production
at scale." Every entry helps others discover the project and understand
its real-world applicability.

## Why Add Your Name?

- 🏢 **Visibility** — show your organization's AI governance maturity
- 🤝 **Community** — connect with other AGT users facing similar challenges
- 📈 **Project health** — help maintainers prioritize features based on real usage
- 🛡️ **Signal** — demonstrate industry adoption for regulatory conversations
4 changes: 3 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -259,7 +259,7 @@ See **[SDK Feature Matrix](docs/SDK-FEATURE-MATRIX.md)** for detailed per-langua
**Compliance & Deployment**
- [Known Limitations](docs/LIMITATIONS.md) — Honest design boundaries and recommended layered defense
- [OWASP Compliance](docs/OWASP-COMPLIANCE.md) — Full ASI-01 through ASI-10 mapping
- [Azure Deployment](docs/deployment/README.md) — AKS, AI Foundry, Container Apps
- [Deployment Guides](docs/deployment/README.md) — Azure (AKS, Foundry, Container Apps), AWS (ECS/Fargate), GCP (GKE), Docker Compose
- [NIST AI RMF Alignment](docs/compliance/nist-ai-rmf-alignment.md) · [EU AI Act](docs/compliance/) · [SOC 2 Mapping](docs/compliance/soc2-mapping.md)

**Extensions**
Expand Down Expand Up @@ -289,6 +289,8 @@ This toolkit provides **application-level governance** (Python middleware), not

- [Contributing Guide](CONTRIBUTING.md) · [Community](COMMUNITY.md) · [Security Policy](SECURITY.md) · [Changelog](CHANGELOG.md)

**Using AGT?** Add your organization to [ADOPTERS.md](ADOPTERS.md) — it helps the project gain momentum and helps others discover real-world use cases.

## Important Notes

If you use the Agent Governance Toolkit to build applications that operate with third-party agent frameworks or services, you do so at your own risk. We recommend reviewing all data being shared with third-party services and being cognizant of third-party practices for retention and location of data.
Expand Down
126 changes: 65 additions & 61 deletions docs/deployment/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,87 +1,91 @@
# Azure Deployment Guides
# Deployment Guides

Deploy the Agent Governance Toolkit on Azure for production-grade runtime security governance of AI agents.
Deploy the Agent Governance Toolkit on any cloud or on-premises infrastructure.

> **No vendor lock-in** — AGT is pure Python/TypeScript/.NET/Rust/Go with zero cloud-vendor
> dependencies. It runs anywhere containers run.
>
> **Quick start:** `pip install agent-governance-toolkit[full]` — see the [main README](../../README.md) for local development.

---

## Deployment Options
## Choose Your Platform

### Azure

| Scenario | Guide | Best For |
|----------|-------|----------|
| **Azure Kubernetes Service (AKS)** | [AKS Sidecar Deployment](../../packages/agent-mesh/docs/deployment/azure.md) | Production multi-agent systems, enterprise HA |
| **Azure AI Foundry Agent Service** | [Foundry Integration](azure-foundry-agent-service.md) | Agents built with Azure AI Foundry |
| **Azure Container Apps** | [Container Apps](azure-container-apps.md) | Serverless, scale-to-zero scenarios |
| **OpenClaw on AKS** | [OpenClaw Sidecar](openclaw-sidecar.md) | Governing OpenClaw autonomous agents |

### AWS

| Scenario | Guide | Best For |
|----------|-------|----------|
| **AWS ECS / Fargate** | [ECS Deployment](aws-ecs.md) | Serverless containers, simple agent deployments |
| **AWS EKS** | [ECS Guide](aws-ecs.md) (Kubernetes section) | Production multi-agent on Kubernetes |

### Google Cloud

| Scenario | Guide | Best For |
|----------|-------|----------|
| **Azure Kubernetes Service (AKS)** | [AKS Sidecar Deployment](../../packages/agent-mesh/docs/deployment/azure.md) | Production workloads needing full control over infrastructure, multi-agent systems, enterprise-grade HA |
| **Azure AI Foundry Agent Service** | [Foundry Integration](azure-foundry-agent-service.md) | Teams building agents with Azure AI Foundry who want governance as middleware |
| **Azure Container Apps** | [Container Apps Deployment](azure-container-apps.md) | Serverless container workloads, rapid prototyping, scale-to-zero scenarios |
| **OpenClaw on AKS** | [OpenClaw Sidecar](openclaw-sidecar.md) | Securing OpenClaw autonomous agents with governance guardrails |
| **Google Kubernetes Engine (GKE)** | [GKE Deployment](gcp-gke.md) | Production multi-agent on GKE |
| **Cloud Run** | [GKE Guide](gcp-gke.md) (Cloud Run section) | Serverless container workloads |

### Self-Hosted / On-Premises

| Scenario | Guide | Best For |
|----------|-------|----------|
| **Docker Compose** | [OpenClaw Sidecar](openclaw-sidecar.md#quick-start-with-docker-compose) | Local development, testing |
| **Private Endpoints** | [Private Endpoints](private-endpoints.md) | Air-gapped / regulated environments |

---

## Architecture Overview

The toolkit supports three primary deployment patterns on Azure:
The toolkit supports three primary deployment patterns on any cloud:

```
┌─────────────────────────────────────────────────────────────────┐
│ Azure │
│ │
│ ┌─────────────────┐ ┌──────────────────┐ ┌───────────────┐ │
│ │ AKS │ │ Container Apps │ │ Foundry Agent │ │
│ │ │ │ │ │ Service │ │
│ │ ┌─────┐┌─────┐ │ │ ┌─────┐┌──────┐ │ │ │ │
│ │ │Agent││Gov │ │ │ │Agent││Gov │ │ │ ┌─────────┐ │ │
│ │ │ ││Side-│ │ │ │ ││Init/ │ │ │ │Governance│ │ │
│ │ │ ││car │ │ │ │ ││Side │ │ │ │Middleware│ │ │
│ │ └─────┘└─────┘ │ │ └─────┘└──────┘ │ │ └─────────┘ │ │
│ │ Pod │ │ Container Group │ │ In-Process │ │
│ └─────────────────┘ └──────────────────┘ └───────────────┘ │
│ │
│ ┌──────────────────────────────────────────────────────────┐ │
│ │ Shared: Azure Key Vault │ Azure Monitor │ Managed ID │ │
│ └──────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
┌────────────────────────────────────────────────────────────────────────┐
│ Any Cloud (Azure / AWS / GCP / On-Prem) │
│ │
│ ┌──────────────────┐ ┌──────────────────┐ ┌─────────────────────┐ │
│ │ Kubernetes (AKS/ │ │ Serverless (ACA/ │ │ Agent Framework │ │
│ │ EKS/GKE) │ │ Fargate/CloudRun)│ │ (Foundry/Bedrock/ │ │
│ │ │ │ │ │ Vertex) │ │
│ │ ┌─────┐┌─────┐ │ │ ┌─────┐┌──────┐ │ │ │ │
│ │ │Agent││Gov │ │ │ │Agent││Gov │ │ │ ┌─────────────┐ │ │
│ │ │ ││Side-│ │ │ │ ││Init/ │ │ │ │ Governance │ │ │
│ │ │ ││car │ │ │ │ ││Side │ │ │ │ Middleware │ │ │
│ │ └─────┘└─────┘ │ │ └─────┘└──────┘ │ │ └─────────────┘ │ │
│ │ Pod / Task │ │ Container Group │ │ In-Process │ │
│ └──────────────────┘ └──────────────────┘ └─────────────────────┘ │
│ │
│ ┌─────────────────────────────────────────────────────────────────┐ │
│ │ Shared: Secret Store │ Monitoring │ Identity Provider │ │
│ │ (Key Vault / Secrets │ (CloudWatch│ (Managed ID / IAM Role / │ │
│ │ Manager / Secret Mgr│ / Monitor)│ Workload Identity) │ │
│ └─────────────────────────────────────────────────────────────────┘ │
└────────────────────────────────────────────────────────────────────────┘
```

---

## Which Option Should I Choose?

**Choose AKS if:**
**Choose Kubernetes (AKS/EKS/GKE) if:**
- You need full control over networking, scaling, and pod configuration
- You're running multi-agent systems with sidecar-per-agent governance
- You require enterprise features: managed identity, Key Vault, zone-redundant HA
- You're deploying OpenClaw or other containerized autonomous agents

**Choose Azure AI Foundry Agent Service if:**
- You're already building agents with Azure AI Foundry
- You want governance as in-process middleware (no sidecar overhead)
- You prefer a managed service over managing Kubernetes infrastructure

**Choose Azure Container Apps if:**
- You want serverless scaling (including scale-to-zero)
- You're running single-agent or small-scale multi-agent scenarios
- You want a simpler operational model than Kubernetes
- You're prototyping before moving to AKS for production

---

## Other Cloud Platforms

| Cloud | Guide |
|-------|-------|
| AWS (EKS/ECS) | [AWS Deployment](../../packages/agent-mesh/docs/deployment/aws.md) |
| GCP (GKE) | [GCP Deployment](../../packages/agent-mesh/docs/deployment/gcp.md) |
| Generic Kubernetes | [Kubernetes Guide](../../packages/agent-mesh/docs/deployment/kubernetes.md) |

---

## Common Azure Resources

All deployment options benefit from these Azure services:
- You require enterprise features: managed identity, secret stores, zone-redundant HA

- **Azure Key Vault** — Store agent private keys, DID secrets, and policy signing keys
- **Azure Monitor / Container Insights** — Collect governance metrics via OpenTelemetry
- **Managed Identity** — Authenticate to Azure services without credentials in code
- **Azure Event Grid** — React to governance events (policy violations, trust score changes)
**Choose Serverless (Container Apps/Fargate/Cloud Run) if:**
- You want scale-to-zero and simpler operational overhead
- You're running single-agent or small-scale scenarios
- You're prototyping before moving to Kubernetes for production

See the [AKS guide](../../packages/agent-mesh/docs/deployment/azure.md) for detailed setup of each.
**Choose In-Process Middleware if:**
- You're using a managed agent framework (Azure AI Foundry, Bedrock, Vertex)
- You want zero sidecar overhead
- Your agents run as functions, not long-lived containers
Loading