OpenIntelligence
OpenIntelligence Summary
OpenIntelligence is a with in-app purchases iOS app in Tools by Gunnar Hostetler. Released in Jan 2026 (2 months ago). It has 3.00 ratings with a 4.67★ (excellent) average. Based on AppGoblin estimates, it reaches roughly 40 monthly active users and generates around $<10K monthly revenue (100% IAP / 0% ads). Store metadata: updated Mar 10, 2026.
Store info: Last updated on App Store on Mar 10, 2026 .
4.67★
Ratings: 3.00
Screenshots
App Description
Turn your documents into an offline neural knowledge base.
Stop digging through PDFs. OpenIntelligence brings enterprise-grade RAG (Retrieval-Augmented Generation) to your iPhone—running entirely on your device.
29-STEP RETRIEVAL PIPELINE. ZERO CLOUD DEPENDENCY.
This is not simple keyword search. OpenIntelligence orchestrates a rigorous 29-step pipeline used by high-end research systems:
• HyDE (Hypothetical Document Embeddings) — Hallucinates an answer to find better semantic matches.
• Hybrid Search — Fuses BM25 keywords with 384-dim neural embeddings for maximum recall.
• Reciprocal Rank Fusion — Mathematically combines retrieval strategies to surface the best hits.
• MMR Diversification — Filters redundant chunks to maximize information gain.
• Cross-Encoder Reranking — Scores every candidate with a dedicated neural model for precision.
• Graph Context Packing — Optimizes the limited token budget using graph theory.
• Parent Document Retrieval — Expands matched sentences to their full paragraph context.
• Lost-in-Middle Mitigation — Reorders context to ensure the AI sees the most critical evidence.
• Semantic Chunking — Splits documents by logic and structure, not just character counts.
• Multi-Column OCR — Metal-accelerated vision processing for complex PDF layouts (360 DPI).
• Agentic Tool Use — Autonomous search, summarization, and comparison capabilities.
• 7 Anti-Hallucination Gates — Every answer passes through verification gates (A-G) that check retrieval confidence, evidence coverage, numeric sanity, contradictions, semantic grounding, quote faithfulness, and generation quality. Critical failures trigger abstention — the AI refuses to answer rather than answer wrong.
• Evidence-First Mode — When your question barely overlaps with retrieved content, the AI states what evidence exists instead of hallucinating a plausible-sounding answer.
• AI Hub Transforms — Extract key facts, step-by-step instructions, plain English, gap analysis, or illustrated visualizations from any response. All grounded in your source documents.
• Motherboard HUD — Real-time X-ray overlay showing Apple Silicon chip positions with live telemetry.
• Rich Response Formatting — Full markdown rendering with headers, bullets, bold text, and code blocks.
• Device-Optimized Performance — 3-tier Metal GPU sha