~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
LearningCircuit/local-deep-research is a research assistant that uses language models and search engines to investigate questions and produce cited reports, while supporting local models, cloud models, and private documents. It is for people who want to conduct research with their own searchable knowledge base and keep their data local and encrypted. The catalogue lists three instructions for working with it.
Latest release v1.10.7 — Release 1.10.7 · 28 Aug 2026
3 files for Codex, OpenCode, Claude Code and Gemini CLI: local-deep-research AGENTS.md, local-deep-research CLAUDE.md, local-deep-research GEMINI.md — 3,828 tokens loaded in every session.
AGENTS.md A 3,818 tok CLAUDE.md A 5 tok GEMINI.md A 5 tok These files are LearningCircuit/local-deep-research's own configuration — they tell Codex, OpenCode, Claude Code and Gemini CLI how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.