local-deep-research – Accelerate scientific answers with any LLM
From the repo · “ ~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.”
Asks an AI to find answers or data for you from the internet or your own computer files.
"A founder named Emma wants to understand a new market trend. She asks the AI to search across academic papers and news articles. After answering a few prompts, the AI gives Emma a concise summary of the trend and the most relevant supporting data. Emma can now use this information to inform her business strategy."
- •You need to conduct research on sensitive or private documents without relying on cloud services
- •You want to utilize multiple search engines and databases, including local and cloud-based LLMs, in one platform
- •You require a high level of encryption and security for your research data and results
python app.py --query 'climate change mitigation' --search-engines arXiv,PubMed --private-docs /path/to/private/documents
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
A prompt/skill package — nothing to install beyond adding it to your AI tool.
mkdir -p ~/.claude/skills/local-deep-research && curl -fsSL https://workflowstacks.com/api/skills/local-deep-research/claude-skill -o ~/.claude/skills/local-deep-research/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Local-deep-research – Accelerate scientific answers with any LLM is a very large Python project (~300k lines across 804 code files, plus 2488 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.
- 1README.mdStart here — what it does and how to install it
- 2package.jsonDependencies and the commands it exposes
- 3src/local_deep_research/__init__.pyInside src/ — the main logic begins here
- 4examples/2008-finicial-crisis.mdA worked example — copy this to get going
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
A prompt/skill package — nothing to install beyond adding it to your AI tool.
mkdir -p ~/.claude/skills/local-deep-research && curl -fsSL https://workflowstacks.com/api/skills/local-deep-research/claude-skill -o ~/.claude/skills/local-deep-research/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/local-deep-research?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Do this with a working workflow
Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.
Related skills
More claude-skill tools founders pair with this one.