LearningCircuit / local-deep-research

Local Deep Research **AI-powered research assistant for deep, iterative research** *Performs deep, iterative research using multiple LLMs and search engines with proper citations* ▶️ Watch Review by The Art Of The Terminal 🚀 What is Local Deep Research? AI research assistant you control. Run locally for privacy, use any LLM and build your own searchable knowledge base. You own your data and see exactly how it works. ⚡ Quick Start **Option 1: Docker Run (Linux)** **Option 2: Docker Compose (Recommended)** CPU-only (all platforms): With NVIDIA GPU (Linux): Open http://localhost:5000 after ~30 seconds. For GPU setup, environment variables, and more, see the Docker Compose Guide. **Option 3: pip install** > Works on Windows, macOS, and Linux. SQLCipher encryption is included via pre-built wheels — no compilation needed. > PDF export on Windows requires Pango (setup guide). > If you encounter issues with encryption, set to use standard SQLite instead. More install options → 🏗️ How It Works Research You ask a complex question. LDR: • Does the research for you automatically • Searches across web, academic papers, and your own documents • Synthesizes everything into a report with proper citations Choose from 20+ research strategies for quick facts, deep analysis, or academic research. Build Your Knowledge Base Every research session finds valuable sources. Download them directly into your encrypted library—academic papers from ArXiv, PubMed articles, web pages. LDR extracts text, indexes everything, and makes it searchable. Next time you research, ask questions across your own documents and the live web together. Your knowledge compounds over time. 🛡️ Security Your data stays yours. Each user gets their own isolated SQLCipher database encrypted with AES-256 (Signal-level security). No password recovery means true zero-knowledge—even server admins can't read your data. Run fully local with Ollama + SearXNG and nothing ever leaves your machine. **In-memory credentials**: Like all applications that use secrets at runtime — including password managers, browsers, and API clients — credentials are held in plain text in process memory during active sessions. This is an industry-wide accepted reality, not specific to LDR: if an attacker can read process memory, they can also read any in-process decryption key. We mitigate this with session-scoped credential lifetimes and core dump exclusion. Ideas for further improvements are always welcome via GitHub Issues. See our Security Policy for details. **Supply Chain Security**: Docker images are signed with Cosign, include SLSA provenance attestations, and attach SBOMs. Verify with: **Security Transparency**: Scanner suppressions are documented with justifications in Security Alerts Assessment, Scorecard Compliance, Container CVE Suppressions, and SAST Rule Rationale. Some alerts (Dependabot, code scanning) can only be dismissed or are very difficult to suppress outside the GitHub Security tab, so the files above do not cover every dismissed finding. Detailed Architecture → | Security Policy → | Security Review Process → 🔒 Privacy & Data Local Deep Research contains **no telemetry, no analytics, and no tracking**. We do not collect, transmit, or store any data about you or your usage. No analytics SDKs, no phone-home calls, no crash reporting, no external scripts. Usage metrics stay in your local encrypted database. The only network calls LDR makes are ones **you** initiate: search queries (to engines you configure), LLM API calls (to your chosen provider), and notifications (only if you set up Apprise). Since we don't collect any usage data, we rely on you to tell us what works, what's broken, and what you'd like to see next — bug reports, feature ideas, and even which features you love or never use all help us improve LDR. 📊 Performance **~95% accuracy on SimpleQA benchmark** (preliminary results) • Tested with GPT-4.1-mini + SearXNG + focused-iteration strategy • Comparable to state-of-the-art AI research systems • Local models can achieve similar performance with proper configuration • Join our community benchmarking effort → ✨ Key Features 🔍 Research Modes • **Quick Summary** - Get answers in 30 seconds to 3 minutes with citations • **Detailed Research** - Comprehensive analysis with structured findings • **Report Generation** - Professional reports with sections and table of contents • **Document Analysis** - Search your private documents with AI 🛠️ Advanced Capabilities • **LangChain Integration** - Use any vector store as a search engine • **REST API** - Authenticated HTTP access with per-user databases • **Benchmarking** - Test and optimize your configuration • **Analytics Dashboard** - Track costs, performance, and usage metrics • **Real-time Updates** - WebSocket support for live research progress • **Export Options** - Download results as PDF or Markdown • **Research History** - Save, search, and revisit past research • **Adaptive Rate Limiting** - Intelligent retry system that learns optimal wait times • **Keyboard Shortcuts** - Navigate efficiently (ESC, Ctrl+Shift+1-5) • **Per-User Encrypted Databases** - Secure, isolated data storage for each user 📰 News & Research Subscriptions • **Automated Research Digests** - Subscribe to topics and receive AI-powered research summaries • **Customizable Frequency** - Daily, weekly, or custom schedules for research updates • **Smart Filtering** - AI filters and summarizes only the most relevant developments • **Multi-format Delivery** - Get updates as markdown reports or structured summaries • **Topic & Query Support** - Track specific searches or broad research areas 🌐 Search Sources Free Search Engines • **Academic**: arXiv, PubMed, Semantic Scholar • **General**: Wikipedia, SearXNG • **Technical**: GitHub, Elasticsearch • **Historical**: Wayback Machine • **News**: The Guardian, Wikinews Premium Search Engines • **Tavily** - AI-powered search • **Google**…