Skip to main content

Sielum — AI Agent EDR

Endpoint Detection & Response for AI Agents — visibility and control over every AI coding assistant running in your organization.

What is Sielum?​

Sielum is a security management platform that monitors and controls AI agents (Claude Code, Cursor, GitHub Copilot, Amazon Q, ChatGPT) on developer workstations. It gives security and IT teams:

  • Visibility — which AI agents are running, which APIs they connect to, which MCP servers they use
  • Alerting — policy violations, unknown agents, unauthorized API connections
  • Control — enforce allowed/denied tool permissions, block AI API domains via firewall rules
  • Compliance — audit log, GDPR data retention, SOC 2 and EU AI Act export reports

Architecture in one diagram​

┌─────────────────────────────────────────────────────────────────┐
│                         Developer Workstation                    │
│                                                                  │
│  ┌──────────────┐   scan    ┌──────────────────────────────┐    │
│  │  AI Agents   │ ◄──────── │         Sielum Agent         │    │
│  │ Claude Code  │           │  (native binary, no Docker)  │    │
│  │    Cursor    │           └──────────────┬───────────────┘    │
│  │   Copilot    │                          │ gRPC + mTLS        │
│  │   Amazon Q   │                          │                    │
│  └──────────────┘                          ▼                    │
└────────────────────────────────────────────────────────────────-┘
                                             │
                                    nginx (TLS termination)
                                             │
                          ┌──────────────────▼──────────────────┐
                          │           Sielum Server              │
                          │  ┌────────────┐  ┌───────────────┐  │
                          │  │  REST API  │  │  gRPC Server  │  │
                          │  └─────┬──────┘  └───────┬───────┘  │
                          │        └────────┬─────────┘          │
                          │           ┌─────▼──────┐             │
                          │           │ PostgreSQL  │             │
                          │           └────────────┘             │
                          └─────────────────────────────────────-┘
                                             │
                                    ┌────────▼────────┐
                                    │  Dashboard (SPA) │
                                    │  React + Vite    │
                                    └─────────────────-┘

Community Edition Quickstart (5 minutes)​

1. Clone and generate certificates​

git clone <your-repo-url> sielum
cd sielum
bash deploy/certs/gen-dev-certs.sh

2. Configure environment​

cp deploy/.env.community.example deploy/.env.community
# Edit deploy/.env.community — set DB_PASSWORD, ADMIN_PASSWORD, JWT_SECRET

3. Start the server stack​

cd deploy && docker compose -f docker-compose.community.yml --env-file .env.community up -d

Wait ~10 seconds, then open:

4. Build and start the agent​

# Build the agent binary
go build -o sielum-agent ./agent/...

# Start with dev config
./sielum-agent start --config deploy/agent-dev.yaml

5. Verify​

After ~60 seconds, refresh the dashboard. You should see:

  • Your workstation listed under Endpoints
  • Detected AI agents under Agents
  • Active API connections under Connections

Supported AI Clients​

ClientDetectionConfig MonitoringMCP ServersEnforcement
Claude Code✅✅ ~/.claude/settings.json✅✅
Cursor✅✅ .cursor/mcp.json✅Stub
GitHub Copilot✅✅ hosts.json—Stub
Amazon Q✅✅ SSO token cache—Stub
ChatGPT Desktop✅Process-based—Stub

Community Edition limits​

The Community Edition is free and self-hosted. It supports up to 5 monitored endpoints and uses local username/password authentication.

For larger deployments, multi-tenant use, or SSO integration, see Sielum Enterprise.

Next steps​