The Cost Comparison

Our Stack

Backend: FastAPI + Go

Database: PostgreSQL Does Everything

Cache: Valkey (not Redis)

Message Queue: NATS (not Kafka)

AI: Hybrid Strategy (80% Local, 20% Cloud)

Monitoring: Grafana Stack

Infrastructure: Scaleway Kapsule

Data: Open Data First

The Result

Try It We built Kyonis, an agent-native KYC/AML compliance API. Before writing a single line of code, we made a critical decision: 100% open-source stack. The result? An 80% reduction in infrastructure costs compared to a proprietary stack. Here's exactly what we use and why. That's €75,000 saved over 18 months. The API layer uses FastAPI (Python) for its async capabilities and auto-generated OpenAPI docs. But for sanctions screening — where we need sub-500ms response times across 100K+ entries — we use a Go microservice with in-memory fuzzy matching. Why not all Go? Because Python has the best AI/ML ecosystem (spaCy, HuggingFace, sentence-transformers). Why not all Python? Because Go gives us 10x throughput on the hot path. No Elasticsearch. No dedicated search engine. PostgreSQL 16 with: One database instead of three. Simpler ops, fewer things that break at 3am. Redis changed its license. Valkey is the Linux Foundation fork — 100% compatible, truly open-source. Drop-in replacement, zero migration effort. Kafka requires ZooKeeper, JVM tuning, and a PhD in distributed systems. NATS is a single binary, 10MB RAM, and handles everything we need. JetStream gives us persistence when required. This is where it gets interesting: 80% of requests never hit a paid API. The local models handle extraction and classification. Claude only steps in for complex reasoning. Grafana + Prometheus + Loki replaces Datadog. Same dashboards, same alerts, zero monthly bill. We chose Scaleway over AWS: 12 data sources, all free: Total data cost at launch: €0/month. We add OpenSanctions (€500/mo) when we hit 50+ paying customers. Free Sandbox plan: 500 verifications/month, no credit card. If you're building a fintech or compliance tool, give it a spin and let me know what you think. Templates let you quickly answer FAQs or store snippets for re-use. as well , this person and/or - pg_trgm for fuzzy name matching (sanctions screening)

- tsvector for full-text search- GIN indexes for fast trigram lookups- Partitioned tables for the audit trail (7-year retention) - Level 1 — Ollama (Mistral 7B): Text extraction, classification, summarization. Cost: ~€0.- Level 2 — spaCy + HuggingFace: NER for names, companies, addresses in KYC documents. Cost: €0.- Level 3 — Claude API (20% of requests): Complex risk profiles, adverse media analysis, regulatory reports. Cost: ~€200-400/mo.- Level 4 — Deterministic rules engine: Hard-coded regulatory thresholds, auditable scoring. Cost: €0. - Kubernetes managed (Kapsule) — no cluster management overhead- Paris datacenter — GDPR native, data stays in France- 3-5x cheaper than equivalent AWS setup- Startup program with up to €36K credits - Sanctions: OFAC, EU, UN, HMT, DFAT (government APIs, free)- Company registries: API Sirene (France), Companies House (UK), SEC EDGAR (US) — all free- Adverse media: GDELT Project (free, updated every 15 minutes)- Offshore leaks: ICIJ database (Panama/Pandora Papers, free)- UBO: OpenOwnership registry (free) - Screens against global sanctions in <500ms- Runs full KYC verification in <3 seconds- Includes explainable reasoning in every response- Is discoverable by AI agents via MCP- Costs €95/month to run (not €5,400) - 🌐 kyonis.com- 📖 Documentation- 🤖 MCP Server for Claude Desktop