local-deep-research
** ~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.**
⭐ 8,859 stars on GitHub · 🍴 787 forks · 📜 License: mit · 💻 Language: Python
What is local-deep-research?
Running agentic AI research workflows entirely on your own hardware used to mean sacrificing accuracy for privacy. Now, you can achieve near-commercial benchmark scores on a single consumer GPU while keeping your prompts, search queries, and documents completely encrypted and
Topics: the project is tagged with popular topics:
- 🏷️
academia - 🏷️
anthropic - 🏷️
arxiv - 🏷️
brave - 🏷️
deep-research - 🏷️
encryption - 🏷️
home-automation - 🏷️
homeserver - 🏷️
local - 🏷️
local-deep-research
📸 Screenshots
Quick install
The project supports Docker Compose:
git clone https://github.com/LearningCircuit/local-deep-research.git
cd local-deep-research
docker compose up -d
Check the README in the repo for required env variables.
Minimum system requirements
| Component | Recommended |
|---|---|
| RAM | 2048 MB |
| CPU | 2 vCPU |
| Disk | 25 GB SSD |
| OS | Ubuntu 22.04 LTS / Debian 12 |
| Docker | 24.0+ |
⚡ Deploy fast on VSIS
Use the VSIS VPS Lite 2GB RAM / 2 vCPU / 25GB SSD (~104k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running local-deep-research smoothly.
🎯 Benefits:
- One-command
docker compose up -ddeploy in 2 minutes - Dedicated IPv4, root access, unmetered domestic bandwidth
- Daily snapshot backup
- Free install assistance from the VSIS team
👉 See matching VPS plans at vsis.net
Resources
- 🔗 GitHub: LearningCircuit/local-deep-research
- 📚 Official docs: see README in the repo
- 💬 Community: GitHub Issues + Discussions
Article compiled from GitHub data on 08/08/2026. Star/fork counts may have changed — see live numbers via the GitHub link.