AI Engineering Practice

Custom AI Systems.
Production-Ready.
Yours to Keep.

We design, build, and deploy AI assistants, autonomous agents, and backend infrastructure — engineered for your workflow, running on your servers, integrated with your tools.

Talk to Phoebe, our AI assistant →

Ten specialised services.
One engineering practice.

Every service we offer is derived from production systems we've already built and run. No guesswork — only proven patterns.

AI Assistant & Agent Development

Custom AI assistants with defined personas, domain knowledge, and real tool access via MCP. Deploy on Telegram, Discord, Slack, WhatsApp, or web — with multi-provider LLM routing and automatic failover.

  • MCP Servers
  • Multi-platform
  • LLM Routing
  • Persona Engineering

Voice AI Pipelines

Complete voice processing from raw audio through Deepgram STT transcription, LLM summarisation, SQLite FTS5 search indexing, and nightly knowledge graph ingestion — fully automated via systemd.

  • Deepgram nova-3
  • Deepgram Aura TTS
  • Auto-pipeline
  • FTS5 Search

Self-Hosted VPS Infrastructure

Production-grade Linux VPS configuration: Docker Engine with compose orchestration, systemd service and timer management, private bridge networking, and socat proxy patterns for safe cross-network access.

  • Docker
  • systemd
  • socat
  • Linux

Knowledge Graph & Persistent AI Memory

Self-hosted Cognee deployment combining LanceDB vector storage, KuzuDB graph database, and SQLite metadata. Your assistant builds semantic memory from documents and conversations, queryable in real time.

  • Cognee
  • LanceDB
  • KuzuDB
  • SQLite FTS5

Custom REST API Development

Lightweight, purpose-built Python REST APIs that expose your data — email, calendar, voice notes, research findings, and LLM usage metrics — to your AI assistant, dashboard, or any other consumer.

  • Python
  • IMAP API
  • CalDAV API
  • SQLite-backed

LLM Operations & Token Budget Management

Pre-send token estimation, model registry, multi-provider smart routing, rate-limit-aware fallback chains, and a full call ledger — every LLM call tracked with estimated vs actual tokens, cost, and latency.

  • Token Estimation
  • Smart Routing
  • Fallback Chains
  • Audit Ledger

Operational Dashboard Development

Self-hosted ToolJet dashboards that aggregate email, calendar, project tickets, voice notes, and AI usage into one command centre — with action buttons that trigger your AI assistant directly from any row.

  • ToolJet
  • Live Data
  • AI Actions
  • Self-Hosted

Email & Calendar Automation

IMAP and CalDAV integration connecting your inbox and calendar directly to your AI assistant and dashboard. Smart newsletter filtering, timezone-aware event parsing, and AI draft-reply workflows.

  • IMAP SSL
  • CalDAV
  • AI Draft Reply
  • Nextcloud

Project Management AI Integration

AI-connected project tracking via MCP — your assistant can list issues, read project status, and create tickets without leaving the conversation. When a decision is made, the assistant suggests and creates the ticket.

  • Paperclip MCP
  • Auto-ticketing
  • Context-aware

Research Automation & Knowledge Capture

Your AI assistant automatically saves every research finding — title, topic, markdown content, sources, and tags — to a persistent, FTS5-searchable library. Everything it has ever researched grows into a living knowledge base.

  • Auto-save
  • FTS5 Search
  • SOUL.md
  • Cognee Ingest

Simple to start.
Powerful in production.

1

Discover

We start with a discovery call to understand your workflow, your tools, and exactly what you want your AI to do — or stop doing manually.

2

Design

We design the architecture: which models, which tools, which integrations, which hosting pattern — and walk you through every decision before writing a line of code.

3

Deploy

We build, test, and deploy the system on your infrastructure. We document everything, hand it over fully, and remain available for iteration.

Battle-tested technologies.
No unnecessary abstractions.

Every technology in our stack earns its place. We use what works at production scale on real infrastructure.

Python 3.11 Claude Sonnet 4.6 GPT-4o Deepgram nova-3 Deepgram Aura TTS MCP Protocol Docker Engine Docker Compose systemd Linux (Ubuntu) SQLite FTS5 LanceDB KuzuDB Cognee ToolJet Telegram Bot API IMAP / imaplib CalDAV / Nextcloud socat OpenAI-compatible APIs GLM-5-turbo PostgreSQL Discord Slack WhatsApp

Built for people who
actually operate things.

Founders & Operators

You need an AI assistant that knows your business — your tickets, your emails, your meetings, your research. We build a private, self-hosted assistant that aggregates everything into one command centre and actually acts on it.

🏢

Businesses Moving Off SaaS AI

You use ChatGPT or a commercial AI tool but want to own your data, control the model, and integrate your internal systems. We migrate you to a self-hosted stack with equivalent or better capability — no lock-in.

🛠

Development Teams

Your product needs AI functionality — voice processing, document intelligence, a knowledge base, or an internal assistant. We design and build the backend AI layer so your team ships faster without reinventing infrastructure.

🤝

Agencies Building AI Products

You want to offer AI assistant and automation services but don't have the deep infrastructure expertise in-house. We build the stack; you deliver it under your brand. White-label engineering partnerships welcome.

We build AI systems
that run, not just demo.

AI-Von is a specialist AI engineering practice focused on production-grade, self-hosted AI systems. We design and build AI assistants, autonomous agents, voice pipelines, knowledge graphs, REST APIs, and operational dashboards — all running on infrastructure you control.

Every system we build is engineered to run reliably on a Linux VPS, integrated with your real tools, and designed for long-term operation. We work in Python, Docker, and modern LLM APIs. We do not sell SaaS. We deliver systems.

Based in South Africa, working globally.

Start a Discovery Call
10+ Services Delivered
100% Self-Hosted Deployments
5+ LLM Providers Integrated
0 SaaS Lock-in

Ready to build
your AI stack?

Every engagement starts with a discovery call to understand your workflow, your tools, and what you want your AI to do. No commitment, no pitch deck — just a conversation.

Or talk to Phoebe right now — click the microphone button in the bottom-right corner.

phil@ai-von.com