Products
Two products. Your entire backend.
Purple8 is the backend your app runs on — storage, search, RAG, workflows, auth, and encryption in one process. DocIntel turns any document into queryable knowledge inside it. Together they replace 20+ services — you build only the frontend.
Purple8
A category of one
A unified AI-native backend — storage, vector search, document store, full-text, workflow orchestration, RAG, auth, and encryption in a single process. No JVM. No external services. Docker image and pip wheel available.
- Write only the frontend — storage, search, RAG, workflows, auth, and encryption are all Purple8
- Storage, vector search, document store, and full-text — one embedded engine, one process, one port
- Native hybrid search with a cost-based query planner — no separate search service
- Three built-in RAG modes: flat vector, graph-augmented, and hybrid retrieval
- Autonomous RAG tuning — the system profiles your corpus and persists optimal retrieval configuration
- Stateful workflow engine: multi-stage pipelines, SLA monitoring, human-approval gates, AI step persistence
- 82-tool MCP agent interface — RBAC-enforced, works with Claude, Cursor, Copilot, and any MCP-compatible agent
- Cross-instance federated queries with human approval gates
- AES-256-GCM envelope encryption via Local, Vault, AWS, GCP, or Azure key management
- Per-tenant storage isolation enforced at the storage layer — not row filtering. Each tenant gets cryptographically separate data partitions with autonomous threat detection.
- Browser-based admin console — zero npm, zero config
Purple8 DocIntel
Document intelligence microservice
A stateless document intelligence microservice that parses 70+ enterprise document formats — including CAD, BIM, sketches, and audio — through a proprietary extraction model and LLM-assisted relationship mapping. Emits structured knowledge directly into Purple8.
- PDF, DOCX, XLSX, PPTX, HTML, EML, EPUB, TXT/CSV — all standard enterprise formats
- IFC/IFCZIP, DXF, DWG, STEP, STL, OBJ, GLTF/GLB, G-code — full CAD & BIM native
- SAP IDocs, financial XML, structured config formats
- Proprietary NER model — two-pass hybrid: named entity extraction + LLM relationship mapping
- Five OCR engines including a self-hosted option — documents never leave your infrastructure
- Self-hosted OCR with proprietary preprocessing, layout detection, and table reconstruction
- 75+ language detection — entity names extracted in their native script
- Five domain extraction profiles: AEC · Contract · Financial · Scientific · General
- Connectors: SharePoint, Confluence, AWS S3, and generic webhook — batch and push modes
- Emits structured knowledge directly into Purple8; sends optimized embedding hints automatically