# OpenCone — On-Device RAG with Pinecone

> On-device RAG for private knowledge bases on iPhone and iPad. (iPhone/iPad app by Gunnar Hostetler.)

- Source: https://appshunter.io/ios/app/opencone/id6744467668 (this page in markdown: same URL + `.md`)
- Developer: [Gunnar Hostetler](https://appshunter.io/developer/1768599987)
- Category: Developer Tools, Productivity
- Price: Free
- Rating: 5.00/5 from 1 App Store ratings
- Age rating: 4+
- Requires: iOS 17.6 · 4 MB
- Languages: American English
- Released: 2025-05-13
- Data updated: 2026-09-03
- Monetization: free
- User reviews in markdown: https://appshunter.io/ios/app/opencone/id6744467668/reviews.md

## What is OpenCone?

Transform your iPhone and iPad into a self-contained RAG powerhouse. Import PDFs, Word docs, code, images, and text into a secure sandbox - extraction, embedding, and semantic search happen with zero lock-in. Point the app at your OpenAI and Pinecone credentials for a private knowledge base that streams grounded, citation-backed answers in real time.

COMPLETE DOCUMENT PIPELINE
• Multi-format extraction: PDF, DOCX, TXT, HTML, Markdown, JSON, CSV, and code
• Apple Vision OCR for on-device image text recognition
• MIME-aware chunking with configurable size and overlap
• Security-scoped bookmarks preserve file access across launches
• Deduplication by path, size, and timestamp fingerprinting
• Live progress tracking with structured logs for every phase

SEMANTIC SEARCH WITH STREAMING
• One-tap queries embed prompts and run similarity search against Pinecone
• Server-Sent Events deliver incremental answer deltas—no blocking spinners
• Citations reference exact chunks with document names and source metadata
• Metadata filters scope searches to specific documents or custom tags
• Conversation memory keeps recent turns in context for coherent follow-ups

GPT-5 REASONING MODEL SUPPORT
• Choose between standard models (GPT-4o, GPT-4o mini) or GPT-5
• Dynamic controls: reasoning effort for GPT-5, temperature/top-p for others
• Unified Responses API with conditional parameterization

RESILIENCE & OBSERVABILITY
• Pinecone health checks surface outages with dismissible banners
• Circuit breaker prevents hammering unhealthy hosts
• Watchdog timers catch stalled streams and trigger fallbacks
• Per-search trace IDs and granular log levels make every stage inspectable
• Error banners auto-dismiss after 8 seconds with user-friendly summaries

SETTINGS & PRIVACY
• Credentials in Keychain via SecureSettingsStore
• Release guardrails prevent accidental key leaks
• Model selection, chunk parameters, top-k defaults, metadata presets persist
• Reset control wipes credentials and history without reinstalling
• Guided onboarding validates API keys before unlocking main interface

POLISHED SWIFTUI EXPERIENCE
• Theme manager with alternate icons and dynamic color schemes
• Reactive MVVM-S architecture decouples views from business logic
• Async/await throughout keeps UI responsive during heavy operations
• Design system components ensure consistency across all tabs

Whether building surgical references, legal research corpora, or personal knowledge vaults, OpenCone delivers production-grade RAG without vendor dashboards or billing surprises.

## Key features

- Multi-format document import (PDF, DOCX, TXT, code, etc.)
- On-device OCR for image text recognition
- Semantic search with streaming answers
- Real-time citations and metadata filtering
- Support for GPT-5 and other advanced models
- Secure credential management in Keychain


## Frequently asked questions about OpenCone

### What file types can OpenCone import?

OpenCone supports a wide range of file types including PDFs, Word documents (DOCX), plain text (TXT), HTML, Markdown, JSON, CSV, and various code formats. It also utilizes Apple Vision OCR for text recognition within images.

### How does OpenCone ensure privacy and security?

All credentials are stored securely in the Keychain using SecureSettingsStore. Release guardrails are in place to prevent accidental key leaks, and a reset control allows users to wipe credentials and history without reinstalling the app.

### Can I use OpenCone offline?

While the core processing and search happen on-device, OpenCone requires access to your OpenAI and Pinecone credentials to function. Therefore, an internet connection is necessary to interact with these services for embedding and reasoning.

### What are the supported AI models in OpenCone?

OpenCone supports standard models like GPT-4o and GPT-4o mini, as well as the advanced GPT-5 model. Users can dynamically control reasoning effort for GPT-5 and temperature/top-p settings for other models.

### How does OpenCone handle large documents or datasets?

The app features MIME-aware chunking with configurable size and overlap to manage large documents effectively. Deduplication by path, size, and timestamp fingerprinting also helps in managing data efficiently.

### What is the update frequency for OpenCone?

OpenCone was last updated on January 19, 2026, indicating active development. The latest version is 2.2.

### Does OpenCone have ads?

No, OpenCone is ad-free. It is a free application with no advertisements present.

### What is the user sentiment for OpenCone based on ratings?

OpenCone has a perfect rating of 5.0 stars from 1 rating, suggesting very positive initial user feedback.

## Version history (last 4 releases)

### 3 — 2026-06-20

This update introduces critical security enhancements, major performance optimizations for document management, and full compatibility with the latest reasoning models.

Performance & UI Optimizations:
- Instant Document Deletion: Upgraded vector deletion logic to use batching. Removing documents from your index is now up to 10x faster.
- Optimistic UI Updates: Deletion of indexes and namespaces now updates instantly in the UI for a much snappier experience.
- Namespace Management: Added a new Namespace deletion option directly in the Documents tab so you can wipe custom namespaces cleanly.
- Background Syncing: Index lists now sync seamlessly in the background across views.

Security & Architecture:
- Secure API Key Storage: API keys are now stored exclusively in the system Keychain via a secure settings store, replacing process environment variables.
- UserDefaults Hardening: Wiped legacy plain-text API credentials from unencrypted UserDefaults storage.
- Reasoning Model Support: Updated API parameters to fully align with latest OpenAI models, including native reasoning effort configuration and completion token limits.

Stability & Bug Fixes:
- Migrated navigation toolbars to cross-platform SwiftUI layouts to improve UI stability.
- Resolved background streaming task retention warnings.
- Expanded unit test coverage across all core services for improved reliability.

### 2.2 — 2026-01-19

Version 2.2 brings GPT-5.2 support, smart prompts, and bunch of other stuff.  I reworked the UI entirely..

GPT-5.2 REASONING MODEL
• Full GPT-5.2 support with 400K context and 128K output tokens
• New reasoning effort levels: Off, Low, Med, High, and Max (xhigh)
• Updated token limits for modern AI capabilities

SMART EXAMPLE PROMPTS
• Contextual prompts based on your selected index and namespace
• Four categories: Discover, Analyze, Extract, Compare
• Tap any suggestion to instantly search
• Prompts adapt when Charts & Calculations is enabled

CHARTS & CALCULATIONS (Code Interpreter)
• Visualize data from your documents as charts
• Calculate totals, averages, and trends
• Extract structured tables and export to CSV/JSON
• Create timelines and comparison visualizations
• Quick Settings panel with sliders and presets
• Haptic feedback and custom system prompts

### 2.0 — 2025-11-17

Version 2.0 brings foundational improvements to answer generation, reliability, and user control.

OPENAI RESPONSES API & GPT-5
• Migrated from Chat Completions to structured Responses API
• Native GPT-5 reasoning model with dynamic effort controls
• Existing models (GPT-4o, GPT-4o mini) continue with temperature/top-p
• Settings UI conditionally renders correct parameters
• Structured "input" field with system/user content arrays

SERVER-SENT EVENTS STREAMING
• Answers stream token-by-token instead of blocking
• Typing indicator appears immediately while waiting
• Stop button cancels mid-generation with clear feedback
• Watchdog timer detects stalls and triggers fallback completion

CONVERSATION MEMORY
• Bounded client mode includes last ~8 messages for context
• Server-managed threads use OpenAI conversation IDs
• Toggle between modes in Settings for privacy preferences
• Follow-ups understand prior exchanges without restating

RESILIENCE & CIRCUIT BREAKER
• Pinecone health checks run before queries with short timeout
• Circuit breaker prevents calls to unhealthy hosts
• Per-search trace IDs tie logs to specific queries
• Error banners auto-dismiss with user-friendly summaries

PRIVACY & RESET FLOWS
• Settings > Data & Privacy exposes credential reset
• Clears Keychain, conversation history, bookmark consent
• Onboarding messaging clarifies missing keys
• Preflight script blocks accidental credential leaks

CITATION STABILITY & POLISH
• Citations enumerate by offset—no duplicate ID warnings
• Logs tab filters with color-coded levels
• Index host transitions emit structured logs
• Improved keyboard handling and haptic feedback

Behind the scenes: upgraded to OpenAI Responses API, added conditional model parameterization, implemented SSE parsing with cancellation, and wired bounded conversation memory. All changes maintain backward compatibility with existing documents and Pinecone indexes.

### 1.0 — 2025-05-13

No release notes.

## Apps similar to OpenCone

| App | Rating | Price | Category |
| --- | --- | --- | --- |
| [SiteAgent AI : Website Manager](https://appshunter.io/ios/app/siteagent-ai-website-manager/id6780267869) | — | Free | Developer Tools |
| [Pocket-Dev](https://appshunter.io/ios/app/pocket-dev/id6762034037) | — | Free | Developer Tools |
| [Basepanel](https://appshunter.io/ios/app/basepanel/id6773879296) | — | Free | Developer Tools |
| [Mono Dash - Made for 1Panel](https://appshunter.io/ios/app/mono-dash-made-for-1panel/id6766814493) | — | Free | Developer Tools |
| [Gradio Spaces](https://appshunter.io/ios/app/gradio-spaces/id6753218161) | 5.0 (2) | Free | Developer Tools |
| [Kodo: AI Code Editor & IDE](https://appshunter.io/ios/app/kodo-ai-code-editor-and-ide/id6781042920) | 5.0 (8) | Free | Developer Tools |

## More apps by Gunnar Hostetler

- [OpenAssistant](https://appshunter.io/ios/app/openassistant/id6692613772)
- [OpenIntelligence](https://appshunter.io/ios/app/openintelligence/id6756559175)
- [OpenResponses](https://appshunter.io/ios/app/openresponses/id6757338355)

All apps by Gunnar Hostetler: https://appshunter.io/developer/1768599987

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-09-03.*