RiNET technical content is protected intellectual property. This platform documents a sovereign-grade civic intelligence operating system. Code inspection, content scraping, and reverse engineering are not permitted.
A sovereign, self-improving AI operating system — AI that builds AI. We turn your existing applications into RiNET-powered platforms that reason, learn, and improve themselves, on sovereign European infrastructure.
This is the view the system has of itself, rebuilt from the same public feed that powers the map above. Nothing here is a screenshot.
Every point is a real unit of the production fleet, a service or a scheduled job, grouped by the product it serves. Bright points are working right now. The numbers refresh every 30 seconds from the platform's own telemetry; names and internals are withheld.
Hosted on three servers in the EU, one encrypted backbone. Scale, not slides: these counters move while you read them. Read the code behind this map.
Compute, front and data live on separate machines joined by an encrypted WireGuard network. A disaster-recovery site in Helsinki keeps a copy. Nothing in the middle belongs to anyone else.
Each line is a product family of the live fleet. The name and the number come straight from the running system.
Everything above runs in production. Most of what makes it work is not on this page. Six reference modules, written like a textbook: every line explained, every assumption stated. Take the idea, never the keys.
Access with no session store. A signed token that proves itself, and a web server that asks before it serves.
How a live system shows its pulse to the world without leaking a single internal name.
Pay once, unlock for a year. The server asks the payment provider, never the browser.
A system that reads its own results, finds what fell short, and proposes the next change.
Answers with a source or no answer at all. Retrieval over a corpus of a million vectors.
Measurement that listens first. What a browser may say, and what it must be asked.
In a country with €2.9B in annual public procurement, 32,375 active statutes, 307,329 legal articles, 1.8 million registered companies, and 70,000 civic associations — the question is never whether the data exists. The question is whether anyone can see through it fast enough to matter.
Croatia is our proof point. The same forensic problem exists in every democracy: fragmented registries, inconsistent identifiers, disconnected financial flows, opaque beneficial ownership chains, statutes that reference other statutes that reference court decisions from fifteen years ago. The data is technically public. It is also, in practice, unreachable.
Existing solutions treat symptoms. Dashboards present what you already knew. BI tools require you to know what question to ask. OSINT platforms dump raw feeds and call it transparency. None of them resolve entities across schemas. None of them reason temporally across thirty years of regulatory change. None of them build the graph.
RiNET does not compete with these tools. It is the substrate beneath them. The layer that makes "who owns this" and "is this legal" and "has this happened before" answerable in under 200 milliseconds, across every public dataset in a sovereign territory, with citation-grade provenance for every answer returned.
RiNET is structured as a vertical cortex — seven distinct computational layers, each responsible for one transformation in the path from raw heterogeneous input to structured, query-ready intelligence. Every layer is independently replaceable. No layer assumes anything the layer below cannot prove.
Every layer exposes a stable internal contract. Every transformation is auditable. Every output is traceable to its source. · Read the full architecture documentation →
Every node above corresponds to a running service in production. This diagram shows the physical topology — three servers, one encrypted backbone, no shortcuts taken in the wire.
Animated packet flows. Real ports. Real services. · Open in full-screen →
It is a reasoning substrate. Every question asked of RiNET descends through the cortex, touches every relevant memory, reconciles against the temporal graph, and returns with a provenance trail. The cortex does not retrieve. It reasons.
RiNET indexes content across seven vector collections, each optimized for a distinct domain: legal text, corporate records, procurement contracts, court rulings, news streams, technical documentation, and conversational memory. Query any language. Retrieve across all.
Semantic search is not enough. RiNET binds every retrieved passage to the resolved entity it describes. A query about "the procurement officer at KBC Rijeka in Q2 2024" returns the person, their role-at-time, the contracts they signed, the outcomes, and the legal framework in effect that quarter.
Every edge carries a validity window. When a company changes ownership, when a statute is amended, when a person leaves a role — the graph does not overwrite. It layers. Ask a question about 2021 and RiNET answers with the state of the world in 2021, not the state of the world today.
Every answer RiNET returns carries an audit chain: source document, extraction model, normalization transform, resolution confidence, graph traversal path. There is no "AI said so." There is only "this answer came from these fifteen documents, reconciled against this statute, as amended on this date."
Continuous scanning identifies patterns that should not exist. Procurement clusters with identical winning margins. Board members appearing across mutually-exclusive competitor structures. Legal entities with matching fingerprints but different names. RiNET finds them. It does not judge them. It surfaces them for the humans who should.
The conversational interface (DABI) is ephemeral by design. Nothing a user asks is retained beyond the session unless explicitly marked for continuity. Sensitive queries leave no trace. Transparent queries build institutional memory. The distinction is user-controlled, cryptographically enforced.
RiNET does not run on a cron schedule. It runs on a swarm. A centralized orchestrator decomposes every operational requirement into atomic tasks, delegates to specialized workers, and reconciles results against a shared ontology. The humans who operate the system talk to exactly one agent. That agent does the rest.
The architecture inverts the usual pattern. Traditional platforms expose dashboards and assume humans will compose the right questions. RiNET exposes a single reasoning partner (DABI) and assumes humans will ask about outcomes. "Flag every procurement contract above €100K awarded in the last twelve months where the winning bidder was incorporated less than six months before the tender announcement" is not a query to build. It is a sentence to type.
Beneath DABI, six hundred and sixty-six specialized agents execute. One central orchestrator. Five core cognitive domains (Legal, Financial, Civic, Sentinel, Journalist). Sixty mid-level coordinators. Six hundred task-specific workers. The number is not symbolic. It is the measured steady-state fleet size under current operational load.
Agents spawn new agents. Agents retire obsolete agents. The swarm rebalances in real time against workload and observed performance. Every agent executes within strict sandboxing. Every agent logs to the same immutable audit trail. The swarm cannot be observed. The swarm's output can be audited to the character.
Numbers are not the product. Numbers are the evidence that the product is real. The following are measured values from production infrastructure as of the current operational quarter.
| Domain | Asset | Volume |
|---|---|---|
| Corporate | Resolved legal entities (companies, institutions, associations) | 1,809,421 |
| Corporate | Beneficial ownership relationships | 447,289 |
| Legal | Statutes, regulations, ordinances (active + historical) | 32,375 |
| Legal | Legal articles indexed and vectorized | 307,329 |
| Legal | Court notices (e-oglasna) with OIB cross-linkage | 92% coverage |
| Financial | RGFI financial statements imported (1996–2025) | 1,864,712 |
| Financial | Pre-2023 records converted HRK → EUR | 100% |
| Procurement | Public tenders indexed (domestic + EU-SIMAP) | 273,118 |
| Procurement | Forensic anomaly findings (critical + high severity) | 1,507 |
| Persons | OIB-enriched individuals with role attribution | 177,041 |
| Asset declarations | Imovinske kartice (public officials) | 161,000+ |
| Vector memory | Indexed passages across seven collections | 6,870,543 |
| Graph | Nodes · Edges | 164,583 · 891,247 |
| Knowledge | DABI Q&A pairs under continuous retrieval | 10,664 |
| Training | LLM fine-tuning records (Croatian legal corpus) | 14,666 |
| Ingestion | Records processed per 24-hour window | ≈180,000 |
| Query latency | Median end-to-end (entity lookup, p50) | 142 ms |
| Query latency | p95 (complex graph traversal) | 487 ms |
| Uptime | Service level (last 90 days) | 99.94% |
| Hallucination rate | Measured across 6,400 evaluator Q&A pairs | 0.3% |
The difference matters. Enterprise-grade security assumes a commercial adversary. Sovereign-grade security assumes a state-level adversary — or a state-level regulator asking whether your claims are true.
AES-256 for all persistent stores. TLS 1.3 minimum for all transport. Per-tenant key derivation. No shared encryption contexts between clients. Key rotation is automated and auditable.
Every administrative action — every data ingestion, every configuration change, every user session — is hashed and anchored to a public proof-of-stake chain (Polygon). The audit trail cannot be altered after the fact without global public evidence of alteration.
Data subject rights are not a feature. They are a schema constraint. Right to access, right to rectification, right to erasure, right to restriction — each is implemented as a first-class database operation with guaranteed propagation across all derivative layers.
A Data Protection Impact Assessment for RiNET requires seventeen pages of policy documentation. We wrote them first, then built the system to satisfy them. Every deployment ships with the DPIA package. No ambiguity. No post-hoc justification.
No service inside RiNET trusts any other service by default. Every internal call carries a cryptographic assertion of origin, scope, and intent. Lateral movement is architecturally impossible, not merely discouraged.
If something goes wrong, the system is optimized for post-mortem. Every operation emits structured telemetry. Every telemetry line is indexed. A forensic investigator can reconstruct any sixty-second window of system behavior to the individual instruction. This is a feature. It is not cheap. It is worth it.
RiNET exposes a structured REST API for entity resolution, graph traversal, semantic search, and forensic pattern queries. Full documentation and live playground access are available to registered developers.
Performance in a civic intelligence context is not about transactions per second. It is about time-to-answer for questions that change policy.
p50: 42 ms p95: 128 ms p99: 342 ms
Resolves a legal entity across OIB, MB, VAT, historical names, aliases, and mergers. Returns full temporal validity map.
p50: 186 ms p95: 487 ms p99: 1.2 s
Three-hop relationship search through beneficial ownership, board overlap, procurement participation, and temporal constraints.
p50: 94 ms p95: 223 ms p99: 610 ms
Multi-collection vector retrieval with entity binding, reranking, and citation assembly. RAGAS score: 3.7 / 5.0.
Peak: 14,800 records/min Sustained: 2,100 records/min
End-to-end including normalization, entity resolution, vector embedding, graph insertion, and audit-log anchoring.
RiNET today answers questions. RiNET tomorrow answers questions that have not been asked yet. The roadmap is not aspirational. It is sequenced.
First county-level production deployment. Regional regulatory integration. Real-time anomaly alerts to oversight bodies.
Five sovereign territories under live RiNET instances. First EU-wide pilot for cross-border procurement monitoring.
Standardized cross-member-state entity resolution. EU-Lex fully integrated. Forensic pattern sharing across national oversight bodies.
Policy impact simulation before legislation passes. Early-warning systems for systemic failure patterns. RiNET as decision substrate for democratic governments.
RiNET is currently in pre-deployment with regional authorities, regulatory bodies, and EU-funded governance initiatives. Full case studies will be published as contractual permissions allow.
Coastal-Mountain County pilot for forensic procurement monitoring, regulatory compliance dashboards, and real-time transparency portal for citizens.
DABI EU Fondovi module in operational use for consultancy workflow automation — matching company profiles to open calls, generating feasibility drafts, drafting legal preambles.
Continuous anomaly feed for investigative journalists. Pattern-based alerts for procurement irregularities, board-overlap detection, and unusual filing patterns across court registries.
Tell us what you run today. We'll show you how the AI RiNET platform turns your existing applications into a sovereign, self-improving AI system — and we can build and operate it for you.