LearningCircuit/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.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 67 days ago, with 104 contributors on GitHub.
Gained 84% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Provides an AI-powered research assistant that performs deep, iterative research using multiple LLMs and search engines with proper citations.
- Ensures full local control and privacy by supporting local and cloud LLMs with encrypted, per-user databases and zero-knowledge data security.
- Use for academic researchers needing comprehensive, citation-backed synthesis from sources like arXiv, PubMed, and private documents.
- Use for developers integrating AI research capabilities into applications via REST API or Python client with customizable search strategies.
- Use for privacy-conscious users running fully local research stacks with Docker and GPU acceleration for secure, offline knowledge base building.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
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
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.
Open http://localhost:5000 after ~30 seconds.
pip install (for programmatic/API usage):
⚠️ Docker is preferred for most users. pip installation requires manual setup of SQLCipher for database encryption—see SQLCipher Guide. Best suited for programmatic integration into existing Python projects.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
903+118
Open issues
1.3K+977
Compared with peers in Cryptography
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| MHSanaei/3x-ui | 49.6K | +448 | 52 | 137 days ago |
| XTLS/Xray-core | 42.8K | +205 | 75 | 1 day ago |
| rclone/rclone | 60.9K | +149 | 75 | 4 days ago |
| mitmproxy/mitmproxy | 46.6K | — | 65 | 8 days ago |
| hummingbot/hummingbot | 21.1K | — | 62 | 48 days ago |
| LearningCircuit/local-deep-research | 9.5K | — | 56 | 67 days ago |
| Category median | 46.6K | +205 | 65 | — |
Discover Repositories
Search across tracked repositories by name or description