Skip to content
SPECIFICTION
Get listed

LocalLens

github.com

Free plan Open source WebWindowsmacOSLinuxSelf-hosted
Visit github.com
Spec score 8.8 #3 of 21 in Reverse Image Search Software

What it is

LocalLens is an offline visual search engine for image and video collections stored locally. It indexes directories recursively into ChromaDB, then searches indexed media using text descriptions and ranks results by similarity. Users can upload an image to find visually similar files, or combine image and text inputs to refine a search. A duplicate finder surfaces duplicate and near-duplicate image pairs using a similarity threshold. Listed formats include JPG, PNG, WebP, MP4 and MKV. The project provides a Gradio web interface and a command-line interface, and can sync indexed folders when files are added or deleted. Supported vision embedding backbones include SigLIP 2, MetaCLIP, DFN-CLIP and CLIP. LocalLens is open-source under Apache-2.0 and has a free plan, with no paid plans or usage limits stated. Portable builds are available for Windows, Linux and macOS; Linux and macOS require Python 3.10 or later and Git. The documented baseline is a 4-core CPU, 8 GB RAM, 0 GB VRAM and 20 MB storage; higher CPU, RAM and VRAM are recommended.

Spec sheet

What it does
LocalLens is an offline visual search engine for local image and video collections.Read 15 Oct 2026 · github.com
Purpose
LocalLens is an offline visual search engine for local image and video collections.Read 5 Oct 2026 · github.com
License
LocalLens is open-source and licensed under Apache-2.0.Read 5 Oct 2026 · github.com
Access restriction
The gallery can be restricted to approved directories through the LOCALLENS_ALLOWED_PATHS environment variable.Read 15 Oct 2026 · github.com
Chroma API
Chroma's documentation describes a small Python API for creating collections and adding, updating and deleting records, consistent with LocalLens's ChromaDB indexing layer.Read 15 Oct 2026 · github.com
Community size
The GitHub repository page showed 23 stars, 5 forks and 152 commits when opened.Read 15 Oct 2026 · github.com
Database
LocalLens stores image embeddings in ChromaDB.Read 15 Oct 2026 · github.com
Directory indexing
It recursively indexes directories and supports incremental synchronization for additions and deletions.Read 15 Oct 2026 · github.com
Documentation depth
Official documentation consists of README instructions plus separate installation and hardware-requirements files.Read 15 Oct 2026 · github.com
Duplicate detection
The product identifies duplicate and near-duplicate image and video pairs using a similarity threshold.Read 15 Oct 2026 · github.com
Embedding models
Available vision backbones include EmbeddingGemma 2 and several SigLIP 2 variants.Read 15 Oct 2026 · github.com
EmbeddingGemma integration
Google's EmbeddingGemma 2 model card describes a 740-million-parameter multimodal embedding model supporting text, images, video and audio.Read 15 Oct 2026 · huggingface.co
Gradio role
Gradio describes itself as a Python framework for building machine-learning web interfaces, which is the web UI technology named by LocalLens.Read 15 Oct 2026 · gradio.app
Hardware baseline
The documented baseline is a four-core CPU, 8 GB RAM, no required VRAM and 20 MB storage.Read 15 Oct 2026 · github.com
Hardware requirements
The documented baseline is a 4-core CPU, 8 GB RAM, 0 GB VRAM, and 20 MB storage; 6+ CPU cores, 12+ GB RAM, and 4+ GB VRAM are recommended.Read 5 Oct 2026 · github.com
Higher-end model cost
The SigLIP 2 512 model is documented as adding about 2.3 GB VRAM, 4 GB RAM and 4.58 GB storage.Read 15 Oct 2026 · github.com
Indexing and sync
It recursively indexes directories into ChromaDB and can sync indexed folders for additions or deletions.Read 5 Oct 2026 · github.com
Install platforms
Portable builds are provided for Windows, Linux, and macOS; Linux and macOS require Python 3.10+ and Git.Read 5 Oct 2026 · github.com
Interfaces
LocalLens provides a Gradio web interface and a command-line interface.Read 15 Oct 2026 · github.com
Licence
The repository declares the Apache-2.0 licence.Read 15 Oct 2026 · raw.githubusercontent.com
Linux and macOS installation
Linux and macOS manual installs require Python 3.10 or newer and Git.Read 15 Oct 2026 · github.com
Maintainer model activity
The maintainer's Hugging Face profile showed six public models and four followers when opened.Read 15 Oct 2026 · huggingface.co
Maker profile
The maintainer's GitHub profile identifies the account as grinnch and lists LocalLens as a public Python repository.Read 15 Oct 2026 · github.com
Media formats
The README lists image and video support, including JPG, PNG, WebP, MP4, and MKV.Read 5 Oct 2026 · github.com
Model availability limitation
The SigLIP 2 384 model page states that the checkpoint was not deployed by any inference provider when opened.Read 15 Oct 2026 · huggingface.co
Model hardware cost
The hardware guide lists EmbeddingGemma 2 as adding about 1 GB VRAM, 2 GB RAM and 1.53 GB storage.Read 15 Oct 2026 · github.com
Model limitation
The EmbeddingGemma 2 model card warns that performance can vary by language and that complex or ambiguous inputs can be difficult.Read 15 Oct 2026 · huggingface.co
Models
Supported vision embedding backbones include SigLIP 2, MetaCLIP, DFN-CLIP, and CLIP.Read 5 Oct 2026 · github.com
Natural-language search
Users can enter text descriptions to retrieve visually matching media ranked by similarity.Read 15 Oct 2026 · github.com
Privacy and access
The project describes itself as offline; its README says the gallery can access any indexed directory by default and offers LOCALLENS_ALLOWED_PATHS to restrict accessible directories.Read 5 Oct 2026 · github.com
Public API and SDKs
The published project exposes CLI commands and Python modules but does not document a public HTTP API or SDK.Read 15 Oct 2026 · raw.githubusercontent.com
Python package metadata
The project requires Python 3.10 or newer and publishes the package name as locallens.Read 15 Oct 2026 · raw.githubusercontent.com
PyTorch platform support
PyTorch documents support for Windows, macOS and Linux installations, matching LocalLens's documented platforms.Read 15 Oct 2026 · pytorch.org
Reverse image search
Users can upload an image to find visually similar local files or combine image and text queries.Read 15 Oct 2026 · github.com
Security statement
The README documents an optional directory allow-list but does not state certifications, compliance programs or a formal security policy.Read 15 Oct 2026 · github.com
SigLIP integration
Google's SigLIP 2 model card supports zero-shot image classification and image-text retrieval through Transformers.Read 15 Oct 2026 · huggingface.co
SigLIP licence
The Hugging Face card for the SigLIP 2 384 checkpoint lists an Apache-2.0 licence.Read 15 Oct 2026 · huggingface.co
Supported formats
The README lists image formats such as JPG, PNG and WebP plus video formats including MP4 and MKV.Read 15 Oct 2026 · github.com
Supported operating systems
The portable package targets Windows, while manual installation is documented for Linux and macOS.Read 15 Oct 2026 · github.com
Update process
Portable installations update with update.bat on Windows or update.sh on Linux/macOS.Read 15 Oct 2026 · github.com
Windows installation
The Windows portable package bundles Python and Git and is documented as requiring no additional dependencies.Read 15 Oct 2026 · github.com

Plans and prices

Free Free Open-source software · local image/video collections · Windows portable build or Python installation on Linux/macOS Read 15 Oct 2026 · github.com
LocalLens Free Open-source software; no paid plans or usage limits stated Read 5 Oct 2026 · github.com

Every LocalLens plan and price →

Strong points and limits

Strong points

  • Searches by text or uploaded image.
  • Includes duplicate and near-duplicate detection.
  • Supports listed image and video formats.
  • Offers web and command-line interfaces.
  • Open-source under Apache-2.0.

Limits

  • Linux and macOS require Python 3.10+ and Git.
  • Gallery can access any indexed directory by default.
  • Recommended hardware exceeds the documented baseline.
  • No free trial is listed.

Who it suits

LocalLens suits people organizing local image or video collections who want text or image-based search and duplicate finding. It is also relevant to users comfortable installing portable software or running a command-line interface.

Verdict

LocalLens combines local media indexing, similarity search and duplicate finding in an offline tool. Review directory access settings and the platform prerequisites before installing.

Where Specifiction places it

Alternatives to LocalLensAll alternatives →