Local Deep Research

Local Deep Research is a privacy-focused artificial intelligence (AI) research assistant that performs systematic research on complex questions.

  • AI
  • Productivity
Local Deep Research is a privacy-focused artificial intelligence (AI) research assistant that performs systematic research on complex questions. It breaks questions into subtasks, searches multiple sources in parallel, verifies information across sources, and creates cited reports in PDF or Markdown. It can run entirely locally with Ollama and SearXNG or use external large-language-model providers. It is useful for homelab users who want private, source-grounded research with per-user encrypted databases, real-time progress tracking, an authenticated application programming interface (API), and an analytics dashboard.

Platform availability

Available on 2 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

74/100 Good

Maintained
100last commit 21 days ago
Popular
809,457 GitHub stars
Easy to install
452 install platforms, install notes, Docker image
Light to run
208 GB minimum RAM, runs on ARM
Security check
86no serious findings, 2 minor, CI, tests, OpenSSF Scorecard 8.3/10

Availability: platform listings confirmed today, links checked 55 days ago

GitHub stars
9,457
Open issues
1270
Last commit
2026-10-31
Latest release
v1.10.7
License
MIT
Activity
rising

Checked 21 days ago - source: GitHub (LearningCircuit/local-deep-research)

Resources & Compatibility

Minimum requirements: 8 GB RAM, 100 MB disk. ARM (e.g. Raspberry Pi) is supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Local companion containers The template ships the Local Deep Research service only. Install Ollama and SearXNG for a fully local setup, or configure external large-language-model and search providers. source
  • SQLCipher installation The README links a SQLCipher installation guide for encrypted per-user databases. source

Fetched 45 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Why is my local SearXNG instance rejected by Local Deep Research?

Private and localhost search-engine URLs are blocked by default since v1.10.3. Set the SearXNG instance URL in the container environment as the operator-approved address, and the URL becomes read-only in the web UI.

Why won't the quick start publish port 5000 in Docker Desktop on Mac or Windows?

The quick start uses host networking, which only works on native Linux. On Docker Desktop it silently fails to publish port 5000.

Where should I store Local Deep Research data in Docker?

Mount a volume at /data and set LDR_DATA_DIR=/data. The quick start uses that path as the app data directory.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads