All Products

400+ integrations + local LLMs + vector DB — one deploy

Complete n8n environment with Ollama (local LLMs), Qdrant (vector search), PostgreSQL. Pre-loaded with AI workflow templates: document Q&A, Slack bots, appointment scheduling, email processing. Deploys via Docker Compose in <5 minutes.

• n8n (latest) with 400+ nodes
• Ollama for local LLMs (Llama 3, Mistral, CodeLlama)
• Qdrant vector DB for RAG
• PostgreSQL for n8n data
• Traefik reverse proxy + auto-SSL
• +3 more

✓ Paddle-compliant: Software product: infrastructure template + workflow JSON. Customer pays for deployable stack, not AI output.

Autonomous agents that run on YOUR server

Deploy Hermes Agent (autonomous ops, memory, skills, cron, Telegram gateway) + OpenCode (headless coding agent) as systemd services. Pre-configured with NVIDIA NIM models, skills library, project templates. Agents start on boot, persist across reboots.

• Hermes Agent v0.21+ (systemd service)
• OpenCode v1.18+ (headless coding agent)
• NVIDIA NIM model routing (free tier)
• 7 built-in coding agents (reviewer, debugger, etc.)
• Telegram/Discord/Slack gateway
• +4 more

✓ Paddle-compliant: Software product: agent runtime + config templates. Customer pays for infrastructure deployment, not agent output.

Private ChatGPT for your docs — deploys in minutes

Complete RAG pipeline: document ingestion (PDF, MD, HTML, Notion, Confluence) → embedding (local or API) → vector search (Qdrant) → chat UI (Open WebUI) → API. Private, no data leaves your server. Pre-configured for internal knowledge, support docs, onboarding.

• Open WebUI (chat interface)
• Qdrant vector DB
• Ollama (local embeddings) or OpenAI/Cohere API
• Document ingestion pipeline (watch folder + API)
• Multi-tenant collections (per team/project)
• +3 more

✓ Paddle-compliant: Software product: RAG pipeline + chat UI. Customer pays for search infrastructure, not generated answers.

Monitor every agent, workflow, and model call

Complete observability for AI systems: Prometheus + Grafana + Loki + Tempo + Pyroscope. Pre-built dashboards for n8n, Hermes, OpenCode, Ollama, Open WebUI. Alerts for: model latency, token costs, error rates, queue depths, GPU memory. One deploy, zero config.

• Prometheus (metrics) + Alertmanager
• Grafana (dashboards + alerting)
• Loki (logs) + Promtail
• Tempo (traces) + OpenTelemetry collector
• Pyroscope (profiling)
• +3 more

✓ Paddle-compliant: Software product: monitoring stack + dashboards. Pure infrastructure, no AI output.

Automated PR reviews on your infrastructure

Deploy a bot that reviews every PR: security (Semgrep), style (ruff/shfmt), complexity, tests, docs. Runs on YOUR runners, posts comments via GitHub App/GitLab webhook. Uses OpenCode agents or local LLMs. Zero code leaves your network.

• GitHub App + GitLab webhook support
• Security rules (Semgrep, 2000+ patterns)
• Style/lint (ruff, shfmt, prettier, eslint)
• Complexity analysis (cyclomatic, cognitive)
• Test coverage enforcement
• +3 more

✓ Paddle-compliant: Software product: bot deployment + review rules. Customer pays for automation infrastructure.

50+ production workflows — import and run

Curated library of n8n workflows for: lead enrichment, document processing, Slack/Email automation, CRM sync, social media, monitoring alerts, data pipelines. Each workflow: tested, documented, parameterized. Import via n8n API or UI. Works with n8n AI Stack above or standalone.

• 50+ workflows across 8 categories
• Categories: Lead Gen, Ops, Dev, Support, Marketing, Finance, HR, IT
• Each: JSON + README + test data + video
• Parameterized (env vars, no hardcoding)
• Versioned + changelog
• +3 more

✓ Paddle-compliant: Digital product: workflow JSON files + documentation. Pure software asset, no services.

VPS + Hermes + OpenCode + Claude Code — ready to code in 15 min

We provision a Contabo VPS (VPS L / XL recommended), deploy Hermes Agent + OpenCode + Claude Code CLI, configure all skills, models, systemd services, hardening, and monitoring. You get root access to a production-ready AI workstation. Includes our optimal config: NVIDIA NIM routing, 180+ skills, multi-profile setup, backup automation, observability stack. Just add your API keys and start building.

• Contabo VPS provisioned (VPS L: 16GB RAM, 800GB SSD, 16 vCPU ~€39/mo or XL: 32GB RAM, 1.6TB SSD, 24 vCPU ~€79/mo)
• Hermes Agent v0.21+ (systemd, multi-profile: ops/dev/research)
• OpenCode v1.18+ (headless coding agent, 7 built-in agents)
• Claude Code CLI (configured with your Anthropic key)
• NVIDIA NIM model routing (free tier) + Ollama local fallback
• +7 more

✓ Paddle-compliant: Software product: VPS provisioning script + full AI stack deployment. Customer pays for infrastructure automation + software stack, not human services.

VPS + 10 Production AI Agents — running on boot

Contabo VPS pre-loaded with 10 production-ready AI agents: Hermes (ops), OpenCode (coding), 3x AVR voice agents (restaurant, insurance, electrician), 2x LKA agents (inbound/outbound), n8n automation, RAG knowledge base, monitoring. All configured as systemd services with auto-start, health checks, and Web UIs. Zero config — just add API keys.

• Contabo VPS L (16GB RAM, 800GB SSD, 16 vCPU ~€39/mo) or XL (32GB RAM, 1.6TB SSD, 24 vCPU ~€79/mo)
• Hermes Agent (multi-profile: ops, dev, research) — autonomous ops
• OpenCode (7 coding agents: reviewer, debugger, refactorer, etc.)
• 3x AVR Voice Agents: Restaurant LeadGen, Insurance ApptSetter, Electricité FR
• 2x LKA Agents: Insurance EN/FR, Restaurant EN/FR
• +7 more

✓ Paddle-compliant: Software product: VPS provisioning + pre-configured AI agent fleet. Customer pays for infrastructure automation + agent configurations, not human services.

VPS + Full AI Dev Environment — code in browser or SSH

Contabo VPS configured as a complete AI development workstation: VS Code Server (code-server), Claude Code CLI, OpenCode, Hermes Agent, Git, Docker, Node.js 22, Python 3.11, PostgreSQL, Redis, Ollama (local LLMs), GitHub CLI, GitLab CLI. Pre-configured with dotfiles, aliases, SSH keys, TMux, Zsh. Access via browser (code-server) or SSH. Ready for AI-assisted development immediately.

• Contabo VPS L (16GB RAM, 800GB SSD, 16 vCPU ~€39/mo) or XL (32GB RAM, 1.6TB SSD, 24 vCPU ~€79/mo)
• VS Code Server (code-server) — full VS Code in browser
• Claude Code CLI (configured with your Anthropic key)
• OpenCode (headless coding agent, 7 built-in agents)
• Hermes Agent (dev profile) — autonomous coding tasks
• +7 more

✓ Paddle-compliant: Software product: VPS provisioning + dev environment automation. Customer pays for infrastructure setup + tooling config, not human services.