LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and your private documents. Everything Local & Encrypted.
Implements an iterative research loop where the LLM autonomously formulates follow-up queries based on initial findings, enabling multi-step reasoning across distributed sources. Built on a modular architecture with pluggable search backends (SearXNG, direct API integrations) and SQLCipher-encrypted local storage for document indexing and retrieval. Integrates via REST API and Python SDK, supporting deployment through Docker Compose with optional GPU acceleration or standalone pip installation.
4,142 stars and 7,173 monthly downloads. Actively maintained with 610 commits in the last 30 days. Available on PyPI.
Stars
4,142
Forks
388
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Monthly downloads
7,173
Commits (30d)
610
Dependencies
70
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/LearningCircuit/local-deep-research"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
hienhayho/rag-colls
Collection of recent advanced RAG techniques.
jeremiahbohr/literature-mapper
Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis,...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
DEEP-PolyU/LinearRAG
Source code of LinearRAG at ICLR'26