22nd of 5 in Search
Local Deep Research
Agentic research assistant with local LLMs, SearXNG and encrypted libraries
- Stars
- 9.2k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Aug 2026
Overview
Runs multi-step research across the web, academic engines and your own documents using Ollama or any OpenAI-compatible endpoint, with a LangGraph agent that picks engines adaptively and writes cited reports. Each user gets an AES-256 SQLCipher database, and egress scopes limit which engines and providers a run may use. Web UI on port 5000 via Docker, Compose or pip, for privacy-focused researchers.
Who it is for: Privacy-focused researchers running everything locally
Strengths
- Reports about 95% SimpleQA fully local on one RTX 3090 with Qwen3.6-27B
- Per-user SQLCipher databases; keys derived from the password, never stored
- No telemetry; Docker images signed with Cosign, with SLSA provenance and SBOMs
- Downloaded sources build a searchable, embedded personal library
Weaknesses
- Needs Ollama (or an LLM endpoint) and SearXNG running separately
- Private or localhost engine URLs are blocked unless an operator env var allows them
- Requires an AVX-capable x86-64 CPU; older CPUs crash with Illegal instruction
- docker run --network host only works on native Linux; Docker Desktop needs Compose
What it needs
- GPU optional
- Docker + Compose
- Needs Ollama or OpenAI-compatible LLM endpoint, SearXNG, SQLCipher (bundled wheels)
- Models: Ollama models (e.g. gpt-oss:20b, Qwen3.6-27B), any OpenAI-compatible endpoint
- port 5000
Also in Search
See all 5| Rank | Project | Score |
|---|---|---|
| 1 | MorphicSearch engine that answers with citations and renders rich inline components | 70 out of 100 |
| 3 | GPT ResearcherResearch agent that writes cited reports from web and local documents | 64 out of 100 |
| #4 | VaneSelf-hosted answer engine with cited sources over SearXNG | 55 out of 100 |
| #5 | MAESTROMulti-agent research platform that writes long reports from documents and web | 30 out of 100 |