Skip to main content

Your knowledge.Your AI.Your servers.

Enterprise-grade generative AI within reach of your SMB. Deploy a RAG assistant over your own documents on a single machine, no per-user licences and not a single byte leaving your company.

See how it works
100%
On your premises
0
Data in the cloud
20+
Supported formats
100+
Languages
The problem

The problem

Many SMBs want to use AI, but the reality is that generic solutions don't understand your internal context, don't work for critical processes, and force you to upload confidential documents to servers you don't control. The result: wasted time, legal exposure, and competitive risk.

The challenge facing European SMBs, 2026

Loss of Control

Confidential documents in the hands of external providers with no guarantees on how they are stored, used, or retained.

Risk 01

Legal Exposure

GDPR, LOPD, and sector regulations violated the moment sensitive data leaves your network.

Risk 02

Competitive Risk

Trade secrets, strategies, and client data accessible to third-party AI platforms.

Risk 03
The Solution

One device. Your network. All your internal knowledge. An assistant that adapts to your company.

TENGWAR arrives as a complete system: hardware and software delivered as a single unit. We connect it to your network, ingest your document library, and your team starts receiving answers with precise citations, all without leaving the building.

Your Documents

contracts.pdf
manuals.docx
policies.xlsx
plans.dwg
+12,847

NVIDIA DGX · 128 GB

On-premises
TENGWAR
Document → queryable knowledge
TENGWAR
ONLINE · 100% LOCAL

Cited Answer

P. How much debt was amortized in 2025 and what is the remaining debt broken down by term?

833 k€ of principal was amortized (visible in CashFlow > Loan Repayments).

EntityLong termShort termTotal
Santander865 k€485 k€1,350 k€
CaixaBank419 k€148 k€567 k€
ICO200 k€200 k€400 k€
Total1,484 k€833 k€2,317 k€
FIN-GT-2025.xlsxFIN-Q4-2025-FINAL.pdf
LIVE

Every answer, auditable to the page.

TENGWAR doesn't make things up. Every claim is anchored to a specific section of the original document. A click on the citation opens the document, PDF or not, on the exact page, with the excerpt highlighted.

No hallucinations
The model only answers about what it has read.
Clause-level traceability
Each citation leads to the exact excerpt in the source document.
Real-time streaming
Answers appear as they are generated.
Quick look

TENGWAR in action

Your knowledge, your AI, your servers, and the workflow your team gets from day one.

Who Is It For

Organizations that need private, secure, and instant access to their accumulated knowledge.

Ideal Sectors

Construction & Engineering

Contracts, project specs, blueprints, safety regulations, compliance documentation

Legal Firms

Case law, client files, contracts, regulatory frameworks, due diligence archives

Healthcare

Clinical protocols, patient records, pharmaceutical documentation, research papers

Manufacturing & Industry

Technical manuals, quality procedures, maintenance logs, supplier specifications

Professional Services

SOPs, internal knowledge bases, SLAs, project documentation, training materials

Energy & Utilities

Inspection reports, regulatory compliance, asset management, safety procedures

Use Cases

Internal Knowledge Base

An employee asks a question about company policy. TENGWAR finds the answer in seconds and cites the exact document, section, and page number.

"What is our policy on remote work for contractors?" → Answer from HR Manual v3.2, page 14

Contract Intelligence

Your legal team needs to find every contract expiring this quarter with automatic renewal clauses. TENGWAR searches across hundreds of documents instantly.

"Which contracts expire before July with auto-renewal?" → 12 contracts identified with clause references

Automated Report Generation

A project manager needs a weekly executive summary based on multiple progress reports. TENGWAR generates a formatted Word document with citations.

"Generate an executive summary from this month's site reports" → Downloadable DOCX with source references

Multilingual Document Access

Your team works with documentation in multiple languages. Ask questions in Spanish, get answers from English, French, or German source documents, automatically.

"¿Cuáles son los requisitos de seguridad del cliente?" → Answer from English safety requirements document

Operations & Compliance Support

A field technician needs the approved procedure for a specific situation. TENGWAR provides the exact steps from the official SOP and cites the source.

"Emergency shutdown procedure for Unit 4" → SOP-2024-087, Section 3.2, Steps 1-8

Everything you need, built in

From document ingestion to AI-generated reports: a secure, intelligent knowledge base for your organization.

Smart Document Ingestion

Upload any document. Our 17-phase pipeline handles structure detection, OCR, language identification, translation, and semantic chunking, automatically.

Hybrid Semantic Search

Finds answers by meaning, not just keywords. Combines vector search, traditional text matching, and a knowledge-graph channel for the most accurate results across your entire document library.

Cross-Language Search

Ask questions in any language and find answers regardless of the document's original language. Automatic detection and translation across 100+ languages.

Agentic AI Capabilities

Goes beyond simple Q&A. TENGWAR autonomously decides when to search documents, browse the web, generate files, or combine multiple sources to answer complex questions. For bigger asks, it launches deep investigations that keep running after you close the chat.

Desktop & Web Access

Native Windows and macOS apps that find your server automatically on the network, keep whole folders in sync, and update themselves with signed installers over a tamper-resistant connection. Plus a full web client for any browser on your network.

Answers in Real Time

See answers as they are generated, no waiting for the full response. The same on desktop, on the web, in every conversation.

On-Demand Document Generation

Generate Word, PDF, and PowerPoint reports directly from AI responses, plus diagrams and charts rendered live in the chat, ready to drop into later reports. Preview everything without leaving the conversation.

Connectors for Your Existing Tools

A growing library of ready-made connectors for the systems your business already runs on, ERPs, public registries, e-invoicing, mail and calendar. Bring real-time business data into every answer, no copy-paste required.

Enterprise-Grade Security

Built for organizations where data confidentiality is not optional.

Authorization Levels

Public

General access for all authenticated users

Confidential

Internal company information, restricted distribution

Secret

Sensitive data: contracts, strategy, financials

Top Secret

Maximum confidentiality, named-individual access only

Department Isolation

Users only access documents from their assigned departments. Combined with clearance levels for precise, auditable access control.

Flexible Authentication

Local login with BCrypt hashing, or SSO via Microsoft Entra ID and Google OAuth2. RSA asymmetric JWT signing. Per-user credential encryption with AES-256-GCM.

Full GDPR/LOPD Compliance

All data processed locally on your hardware. Zero transfers to third parties. Complete lifecycle control, from ingestion to deletion.

Governance, woven through every step

Not a separate layer, it surrounds every interaction with your data.

  • Auth gate
  • Bounded execution
  • Tool authorization (default-deny)
  • SSRF guard
  • Audit log
  • Per-document ACL re-check
  • Credential encryption

Adapts to You, Privately

The more you use it, the better it answers. And everything it learns about you stays on your server.

Learns how you work

It remembers your preferences, your topics and the way you ask for things, so every answer fits you a little better.

You have the last word

Review what it has learned, correct it, or erase it whenever you want. Nothing is stored behind your back.

Tell it who you are

A personal note tells TENGWAR how to treat you: your role, your style, your rules.

Private by design

What it learns about you never leaves your company and is never shared with other users.

Integrations

Plug TENGWAR into the systems you already use, without ever leaving your network.

Connector ecosystem: an on-prem TENGWAR appliance surrounded by isolated Docker-sidecar connectors, grouped by category, with NetSuite drawn outside the inner ring as the only cloud connector.OdooFacturaScriptsDynamics 365 BCSAP Business OneSage 50cloudNetSuiteBOEBORMECatastroSpanish UtilsVeriFactuFacturae 3.2TicketBAIMail & CalendarE-signAEMETAEMPS CIMABDNSPLACSPCENDOJDEHúLexNETERPPublic dataComplianceCommunicationVertical SpainPublic admin

ERP connectors

Read your operational system of record, customers, suppliers, invoices, orders, accounting, inventory.

Odoo

Read customers, suppliers, invoices, sales / purchase orders, accounting balances and live inventory directly from Odoo (XML-RPC, read-only).

Available
FacturaScripts

Same canonical surface against the open-source SME ERP, plus a no-effect "draft invoice" preview helper.

Available
Microsoft Dynamics 365 Business Central

Mid-market on-prem ERP integration over OData v4 with Entra ID / Azure AD authentication.

Coming soonComing soon
SAP Business One

REST Service Layer adapter with the same canonical surface.

Coming soonComing soon
Oracle NetSuite

The single cloud-touching ERP connector, SuiteTalk REST + SuiteQL, with an explicit threat-model exception.

Coming soonComing soon
Sage 50cloud Spain

Direct ODBC against the customer's MS SQL Server (no Sage API needed); read-only by hard guarantee at startup.

Coming soonComing soon

Spanish public data & legal intelligence

Search and monitor the regulator's gazette and registries that drive Spanish business decisions.

BOE, Boletín Oficial del Estado

Search and monitor Spanish state regulations by date, section, department, free text. Pull full XML, set term watches, follow regulatory cross-references. SQLite + FTS5 cache absorbs upstream rate limits.

Available
BORME, Boletín Oficial del Registro Mercantil

Province-scoped commercial-registry bulletin discovery for any Spanish company; daily summaries, province watches, structured PDF references for the ingester.

Available
Catastro

Property search by reference or address, retrieval of non-protected cadastral data, and map context, for construction, lender underwriting, due diligence.

Coming soonComing soon

Spanish compliance & e-invoicing

Validate, sign and submit invoices and tax artefacts to AEAT, FACe and the Basque haciendas.

Spanish Utils (AEAT toolkit)

Embedded Spanish compliance toolkit: NIF/CIF/IBAN/postal/phone validation, IVA & IRPF tables, fiscal calendar, Modelo lookup (303, 100, …), CSB43/Norma 43 bank-statement parsing, XAdES-EPES signing with your configured certificates. Pure compute, no external calls.

Available
VeriFactu

Compose, sign and submit invoice records to AEAT under the RD 1007/2023 anti-fraud regime; track lifecycle.

Coming soonComing soon
Facturae 3.2.x

Build, validate, sign and submit Facturae XML to FACe / FACeB2B for public-sector invoicing.

Coming soonComing soon
TicketBAI

Compose, chain and submit anti-fraud invoices to the three Basque haciendas forales.

Coming soonComing soon

Communication & productivity

Mail, calendar and electronic signature, protocol-based and provider-neutral.

Mail & Calendar

One protocol-based connector for any standards-compliant provider: search, thread reading, deadline & commitment extraction, draft preparation, send-with-confirmation, event listing and event creation with confirmation. Replaces today's in-backend Email & Calendar tools.

Coming soonComing soon
E-sign

Prepare a signature request, dispatch with confirmation, poll status, download signed evidence; provider-neutral with Signaturit, Viafirma and Docuten as adapters.

Coming soonComing soon

Vertical Spain

Domain-specific Spanish public sources, meteorology, pharmaceutical safety, grants, procurement, jurisprudence.

AEMET

Spanish meteorological data, forecasts, historicals, weather alerts; valuable for construction, insurance, energy, agriculture verticals.

Coming soonComing soon
AEMPS CIMA

Spanish pharmaceutical safety database, drug lookups, contraindications, batches; healthcare-vertical workhorse.

Coming soonComing soon
BDNS

Spanish national grants database, search public subsidies and funding programmes by region, sector, deadline.

Coming soonComing soon
PLACSP

Spanish public-procurement platform, discover bids, contracts and tender deadlines.

Coming soonComing soon
CENDOJ

Spanish court decisions and case law, search jurisprudence, retrieve full sentencias.

Coming soonComing soon

Public administration

Notifications and court filings from the Spanish public administration, read-only by hard contract.

DEHú

Read-only metadata + deadline extraction from the Spanish public-admin notifications system. Requires customer X.509 certificate.

Coming soonComing soon
LexNET

Read-only metadata from the Spanish court filing system. Requires customer X.509 certificate.

Coming soonComing soon
Deployment

From delivery to production in weeks, not months.

TENGWAR arrives as a complete system. No complex integration projects, no cloud setup.

1

Discovery

We assess your documents, security requirements, and team structure.

1 week
2

Deployment

Hardware delivered and configured on-site. Initial ingestion and permissions.

1-2 weeks
3

Validation

Your team tests with real documents. We fine-tune search and permissions.

1 week
4

Production

Full rollout across departments with user training included.

Ongoing

Includes remote support, software updates, and model upgrades. On-site support available in Spain.

Under the hood

Want to see what's inside?

17
processing phases for every document
4
search channels running in parallel
100%
operated and audited from your network
See the full architecture
Full demo

Watch the full demo

A complete walkthrough of the application: chat, citations, generated documents and reports, and the day-to-day private workflow. Audio in Spanish.

Experience the Interface

A modern, intuitive interface designed for productivity.

Secure Sign-In

Click anywhere or press ESC to close

Frequently Asked Questions

Does any data leave my network?

No. TENGWAR runs entirely on hardware installed at your premises. All document processing, AI inference, and search happens locally. There are zero external API calls, zero cloud dependencies, and zero data transfers to third parties.

What hardware is required?

TENGWAR is delivered pre-installed on an NVIDIA DGX Spark with 128GB of unified memory, a Grace ARM64 CPU, and a Blackwell GB10 GPU. This single device runs the entire platform, no server room required. It connects to your network like any other appliance.

How many documents can it handle?

TENGWAR is designed for enterprise-scale document libraries. The system scales with your needs, from hundreds to tens of thousands of documents across multiple departments and security levels.

Does it work with documents in multiple languages?

Yes. TENGWAR ingests documents in their original languages and translates them at indexing time into your deployment's configured working language. You can ask questions in any supported language, answers arrive in your team's working language with citations back to the original document. This makes cross-language search seamless without per-user language switching.

How accurate are the answers?

TENGWAR uses a hybrid search approach combining semantic understanding with traditional keyword matching, followed by a cross-encoder reranking stage. Every answer includes citations pointing to the exact source document, page, and passage, so your team can always verify. For low-confidence results, TENGWAR re-runs retrieval with corrected queries (Self-RAG / Corrective RAG) and combines multi-query expansions (RAG-Fusion), significantly reducing hallucinated or incomplete answers.

What is the knowledge graph?

During ingestion TENGWAR extracts subject–relation–object facts from your documents, resolves contradictions between them, and assembles everything into a corpus-wide graph. At query time a graph walk runs alongside semantic and keyword search, so questions that span several documents, who supplies what, which contract covers which site, get grounded answers. You can also explore the graph visually and jump from any fact to its source document.

Is it GDPR compliant?

Yes. Because all data stays on your premises, there are no cross-border data transfers and no third-party processing. You maintain complete control over the data lifecycle, from ingestion to deletion. TENGWAR is designed for GDPR and Spanish LOPD compliance from the ground up.

Can different departments have different access levels?

Yes. TENGWAR includes a four-level security clearance system (Public, Confidential, Secret, Top Secret) combined with department-based isolation. Users only see documents they are authorized to access based on both their clearance level and department assignment.

What file formats are supported?

18 formats including PDF, DOCX, XLSX, PPTX, images (with OCR), CSV, JSON, XML, HTML, Markdown, and plain text. Documents are processed through an 18-phase intelligent pipeline that handles structure detection, text extraction, and semantic indexing automatically.

How long does deployment take?

Typical deployment takes 2-4 weeks from initial discovery to full production rollout. TENGWAR arrives as a pre-configured system, there is no complex integration project or cloud setup required.

What ongoing support is included?

TENGWAR includes remote technical support, software updates, and AI model upgrades. On-site support is available for organizations in Spain.

Does TENGWAR plug into our ERP?

Yes, via dedicated MCP connectors. Available today: Odoo, FacturaScripts. Coming soon: Microsoft Dynamics 365 BC, SAP Business One, Oracle NetSuite, Sage 50cloud Spain. Connectors are isolated Docker sidecars in your network, adding an integration does not redeploy your stack.

Can different users get different answers from the same documents?

Yes. Per-user memory, per-user personal prompts, per-user clearance level and department membership all influence retrieval and synthesis. Personal-prompt content is never logged in telemetry.

Where do email and calendar live?

In a single Mail & Calendar MCP that talks IMAP / SMTP for mail and CalDAV for calendar, so it works with whichever provider IT runs (self-hosted, Gmail, Microsoft 365, Fastmail, ProtonMail Bridge, …). Sends are gated by explicit confirmation. Status: coming soon.

Do you support Spanish public-sector data?

Yes: BOE and BORME today; Catastro, AEMET, AEMPS CIMA, BDNS, PLACSP, CENDOJ, DEHú and LexNET coming soon, all as isolated MCP connectors with their own configuration.

Who watches the agent?

Default-deny tool registry; SSRF guard on web tools; per-document ACL re-check inside the Qdrant query at retrieval time; full audit log filterable by user, department, tool, date and status. Personal-prompt content and sensitive tool args are redacted in audit records. Risky tool calls can pause for human approval: the reviewer sees each argument in a structured form, edits are tracked as field-level diffs, and every approval links to its audit trace.

Can TENGWAR work on tasks that outlive a chat?

Yes. Deep investigations, bulk analysis, periodic digests and document generation run as durable jobs: you enqueue them, disconnect, and collect the results from a job inbox when they finish. Jobs can be cancelled or resumed, and administrators can see every job across all users.

TENGWAR

Enterprise AI Without Compromise

See how TENGWAR works with your documents. We'll set up a private demo with your real use case.

100%
Private
18
Formats
100+
Languages

Contact Us