Modular, open-source RAG infrastructure you deploy on your own terms.
Plug in any LLM provider, vector store, or pipeline, keep data on-premises, and extend with vertical modules like e-learning, all through configuration rather than code forks.
- Platform engineers / DevOps teams deploying RAG at their organization with data sovereignty requirements
- Developers building RAG-powered applications via SDKs
- Domain specialists (e.g., university e-learning teams) using vertical modules without touching infrastructure
Unlike RAG toolkits (LangChain, LlamaIndex, Haystack), Vektra ships as a deployable platform:
| Aspect | Toolkits | Vektra |
|---|---|---|
| Deployment | Build your own | docker compose up |
| Configuration | Code changes | YAML/environment |
| On-premises | DIY | First-class support |
| GDPR compliance | DIY | Built-in (retention, audit logs) |
| Vertical features | None | E-learning module included |
git clone https://github.com/vektralabs/vektra-stack.git
cd vektra-stack
cp .env.example .env
# Edit .env: set VEKTRA_LLM_PROVIDER and your LLM API key
docker compose up -d
make demoSee docs/getting-started/ for the full walkthrough. Target: from clone to first RAG query in under 30 minutes.
Vektra uses a hybrid monorepo approach (ADR-0001):
vektra-stack/ # This repository (monorepo)
├── vektra-core/ # RAG engine, LLM abstraction
├── vektra-ingest/ # Document processing (PDF, OCR, PPT, Word)
├── vektra-index/ # Vector store abstraction, embedding
├── vektra-analytics/ # Metrics, reporting, alerting
├── vektra-learn/ # E-learning vertical (chatbot, dashboard)
├── vektra-admin/ # System administration
├── docs/ # Documentation
└── docker-compose.yml # Orchestration
# Separate repositories (different tech stack or deployment target)
vektra-moodle/ # Moodle LMS adapter (PHP plugin)
vektra-sdk-py/ # Python SDK (published to PyPI)
vektra-sdk-js/ # JavaScript SDK (published to npm)
┌───────────────────────────────────────────────────────────────────┐
│ VERTICALS Domain solutions (vektra-learn for e-learning)│
├───────────────────────────────────────────────────────────────────┤
│ LMS ADAPTERS Platform integrations (vektra-moodle, etc.) │
├───────────────────────────────────────────────────────────────────┤
│ CORE RAG engine, ingestion, indexing, analytics │
├───────────────────────────────────────────────────────────────────┤
│ OPERATIONS System administration (vektra-admin) │
├───────────────────────────────────────────────────────────────────┤
│ INTEGRATION SDKs (Python, JavaScript) │
└───────────────────────────────────────────────────────────────────┘
See ROADMAP.md for the full development plan.
| Phase | Focus | Status |
|---|---|---|
| Phase 1 | MVP (core + ingest + index + minimal admin) | Complete |
| Phase 2 | Verticals (learn + moodle + analytics) | Complete |
| Phase 3 | Ecosystem (SDKs, plugins) | Planned |
- docs/ - Full documentation (quick start, API reference, configuration, error codes)
- CHANGELOG.md - Release history
- ROADMAP.md - Development phases and milestones
- GOVERNANCE.md - Project governance and contributor ladder
- CONTRIBUTING.md - How to contribute
- SECURITY.md - Vulnerability reporting policy
- .s2s/decisions/ - Architecture Decision Records
We welcome contributions! Please read CONTRIBUTING.md for guidelines on:
- Developer Certificate of Origin (DCO) sign-off
- Conventional Commits format
- PR workflow
Apache License 2.0. See LICENSE for details.
Vektra is maintained by VektraLabs.