LocalLens
LocalLens is an offline visual search engine for image and video collections stored locally.
What LocalLens is
LocalLens is an offline visual search engine for image and video collections stored locally. It indexes directories recursively into ChromaDB, then lets users search indexed media with text descriptions and ranks results by similarity. Users can also upload an image to find visually similar files, or combine an image with text to refine results. A duplicate finder surfaces duplicate and near-duplicate image pairs using a similarity threshold. Listed formats include JPG, PNG, WebP, MP4 and MKV. LocalLens provides both a Gradio web interface and a command-line interface, and can sync indexed folders when files are added or removed. Supported vision embedding backbones include SigLIP 2, MetaCLIP, DFN-CLIP and CLIP. The open-source project is licensed under Apache-2.0 and is free, 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 specifications are recommended.
Good
- Offline search for local image and video files
- Text and reverse-image search options
- Includes duplicate and near-duplicate detection
- Free and open-source under Apache-2.0
- Portable builds for Windows, Linux and macOS
Watch out
- Linux and macOS require Python 3.10+ and Git
- Gallery can access any indexed directory by default
Who it suits
It suits people who want to search local image and video collections by description or visual similarity. Users who want to limit which indexed directories the gallery can access can configure LOCALLENS_ALLOWED_PATHS.
Verdict
LocalLens provides local-media search, similarity matching and duplicate finding through web and command-line interfaces. Its default directory access is broad, so users who want restrictions should configure the allowed paths.
Plans and prices
From LocalLens's own pricing page, checked 15 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Free | Free | Open-source software · local image/video collections · Windows portable build or Python installation on Linux/macOS |
| LocalLens | Free | Open-source software; no paid plans or usage limits stated |
The facts
Each one read from LocalLens's own pages, with the date it was checked.
What it does
- Access restriction
- The gallery can be restricted to approved directories through the LOCALLENS_ALLOWED_PATHS environment variable.checked 15 Oct 2026
- 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.checked 15 Oct 2026
- Community size
- The GitHub repository page showed 23 stars, 5 forks and 152 commits when opened.checked 15 Oct 2026
- Database
- LocalLens stores image embeddings in ChromaDB.checked 15 Oct 2026
- Directory indexing
- It recursively indexes directories and supports incremental synchronization for additions and deletions.checked 15 Oct 2026
- Documentation depth
- Official documentation consists of README instructions plus separate installation and hardware-requirements files.checked 15 Oct 2026
- Duplicate detection
- The product identifies duplicate and near-duplicate image and video pairs using a similarity threshold.checked 15 Oct 2026
- EmbeddingGemma integration
- Google's EmbeddingGemma 2 model card describes a 740-million-parameter multimodal embedding model supporting text, images, video and audio.checked 15 Oct 2026
- Embedding models
- Available vision backbones include EmbeddingGemma 2 and several SigLIP 2 variants.checked 15 Oct 2026
- Gradio role
- Gradio describes itself as a Python framework for building machine-learning web interfaces, which is the web UI technology named by LocalLens.checked 15 Oct 2026
- Hardware baseline
- The documented baseline is a four-core CPU, 8 GB RAM, no required VRAM and 20 MB storage.checked 15 Oct 2026
- 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.checked 5 Oct 2026
- Indexing and sync
- It recursively indexes directories into ChromaDB and can sync indexed folders for additions or deletions.checked 5 Oct 2026
- Interfaces
- LocalLens provides a Gradio web interface and a command-line interface.checked 15 Oct 2026
- Licence
- The repository declares the Apache-2.0 licence.checked 15 Oct 2026
- License
- LocalLens is open-source and licensed under Apache-2.0.checked 5 Oct 2026
- Maintainer model activity
- The maintainer's Hugging Face profile showed six public models and four followers when opened.checked 15 Oct 2026
- Media formats
- The README lists image and video support, including JPG, PNG, WebP, MP4, and MKV.checked 5 Oct 2026
- Model availability limitation
- The SigLIP 2 384 model page states that the checkpoint was not deployed by any inference provider when opened.checked 15 Oct 2026
Money
- 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.checked 15 Oct 2026
- Model hardware cost
- The hardware guide lists EmbeddingGemma 2 as adding about 1 GB VRAM, 2 GB RAM and 1.53 GB storage.checked 15 Oct 2026
Where it runs
- Install platforms
- Portable builds are provided for Windows, Linux, and macOS; Linux and macOS require Python 3.10+ and Git.checked 5 Oct 2026
- Linux and macOS installation
- Linux and macOS manual installs require Python 3.10 or newer and Git.checked 15 Oct 2026
The company
- Maker profile
- The maintainer's GitHub profile identifies the account as grinnch and lists LocalLens as a public Python repository.checked 15 Oct 2026
The full review of LocalLens
LocalLens is an offline visual search engine for image and video collections stored on your devices. It suits people who want to find and compare files in their own folders, rather than search the wider web. Its range of search methods and open-source licensing make it a capable no-cost option, provided you are comfortable setting up and securing access to your indexed directories.
Overview
LocalLens turns indexed folders into a searchable media collection through a web interface or command line. Search results are ranked by visual similarity, so the app is useful for locating files that resemble a description or reference image, but it is not a general web-search service. The offline design favors privacy-conscious users managing their own libraries; the default directory access calls for care if you expose the gallery to others.
Key features
Search by text and image
Describe what you are looking for and LocalLens ranks indexed media against that description. Alternatively, upload an image to find visually similar files, or combine an image with text to refine results. This flexibility is valuable when a collection is too large to browse manually, though similarity ranking is not the same as an exact-match guarantee.
Indexing and duplicate finding
LocalLens recursively indexes directories into ChromaDB and can sync indexed folders to reflect additions and deletions. That makes it better suited to a changing library than a static, one-off scan. Its duplicate finder surfaces duplicate and near-duplicate image pairs using a similarity threshold. The threshold can help flag likely repeats, but near-duplicates still merit human review before deleting anything.
Models, formats and interfaces
Supported vision embedding backbones include SigLIP 2, MetaCLIP, DFN-CLIP and CLIP. Supported media includes JPG, PNG and WebP images and MP4 and MKV video. A Gradio web UI serves visual browsing and search, while a command-line interface offers another way to work with the collection.
Privacy and access
The project describes LocalLens as offline, a useful distinction for users who want search over personal media without relying on a web-based image service. However, the gallery can access any indexed directory by default. If other people can reach the web interface, configure LOCALLENS_ALLOWED_PATHS to restrict accessible directories rather than assume indexing itself limits what the gallery can show.
Pricing
LocalLens is free open-source software under the Apache-2.0 license. Its LocalLens plan costs free, and no paid plans or usage limits are stated. There is no free trial because the software is free outright. That makes it a straightforward choice for users willing to run it themselves; there is no lower-cost hosted tier to trade setup effort for convenience.
Platforms
LocalLens supports Linux, macOS, Windows, web, and self-hosted use. Portable builds are provided for Windows, Linux and macOS; Linux and macOS installations require Python 3.10+ and Git. The documented baseline is a 4-core CPU, 8 GB RAM, 0 GB VRAM and 20 MB storage, with 6+ CPU cores, 12+ GB RAM and 4+ GB VRAM recommended. The modest baseline can suit a machine without a dedicated GPU, while the recommended specifications are a more comfortable target for larger or more demanding libraries.
Who it's for
LocalLens is a strong fit for people with growing local photo or video libraries who want text search, visual matching and duplicate discovery in one self-hosted tool. It is less suitable for anyone seeking broad internet image search, a managed service, or a polished workflow that avoids local installation and access configuration.
Pros and cons
- Pros: Text, image and combined search give several ways to locate similar files in a personal collection.
- Pros: Folder syncing accounts for additions and deletions, while the duplicate finder can surface near-repeats as well as duplicates.
- Pros: Offline operation, open-source licensing and a free plan avoid subscription costs and fit privacy-conscious self-hosting.
- Cons: The gallery can access any indexed directory by default, so users sharing the web interface should restrict paths deliberately.
- Cons: Linux and macOS installations require Python 3.10+ and Git, adding setup work for users who prefer a fully managed app.
- Cons: Similarity-based results and thresholded duplicate pairs require judgment; the tool does not promise exact matches.
Alternatives
For a wider range of reverse-image-search options, browse Reverse Image Search Software.
Choose Lenso.ai if you want a freemium service spanning Android, iOS, browser extensions and other platforms, with Starter features that include 50 unlocks, 10 alerts and unlimited searches, or a Developer plan with 5,000 API calls.
Imagga Visual Search is an alternative for API-focused users who also need background removal, barcode recognition and OCR; its Indie plan is $79 a month, billed monthly, and includes 70,000 API requests.
Pick SearchReverseImage for free, unlimited photo searches on Android, iOS or web, with no signup or watermark and support for JPG/JPEG, PNG, WEBP or GIF images up to 4 MB.
ImageRights Discovery is another free option, with an ImageRights Pilot plan covering the first 100 images.
Pixsy is a better fit for monitoring images: its free plan monitors 500 images and includes regular-priority match scanning and unlimited case submission, but allows 0 takedown notices and limited import sources.
Reverse Image Search Anywhere is a free alternative for Android, browser-extension and web use.
RIMG offers free reverse-image searches on Android, iOS and web, with no usage limit stated.
SerpApi is an API-oriented alternative; its free plan includes 250 searches per month and 50 throughput per hour.
Verdict
Choose LocalLens if you want a free, open-source way to search and deduplicate your own local images and videos without sending the collection to an online search service. Its combination of text, image and duplicate search is the main reason to choose it. Look elsewhere if you need web-wide image search or want to avoid local setup and the responsibility of restricting gallery access.
Getting started
- Visit https://github.com/meangrinch/LocalLens.
- Choose a portable build for Windows, Linux, or macOS.
- For Linux or macOS, have Python 3.10+ and Git available.
- Index the directories containing the media you want to search.
- Use the Gradio web interface or command-line interface; set LOCALLENS_ALLOWED_PATHS to restrict accessible directories.
Questions
How much does LocalLens cost?
LocalLens is free, with no paid plans or usage limits stated.
Is LocalLens open-source?
Yes. It is licensed under Apache-2.0.
Which operating systems are supported?
Portable builds are provided for Windows, Linux, and macOS. Linux and macOS require Python 3.10 or later and Git.
What image and video formats are supported?
Listed formats include JPG, PNG, WebP, MP4, and MKV.
Does LocalLens work offline?
Yes. The project describes LocalLens as an offline visual search engine for local collections.
What are the documented hardware requirements?
The baseline is a 4-core CPU, 8 GB RAM, 0 GB VRAM, and 20 MB storage. The project recommends 6 or more CPU cores, 12 GB or more RAM, and 4 GB or more VRAM.
Alternatives to LocalLens
- 1
Berify
Free planAndroidiOSWebAPI8.0From $5.95 a month - 2

Reverse Image Search Anywhere
Free planOpen sourceAndroidWebExtensionLinux7.8Free plan - 3

Pixsy
Free planWebAPI7.4From $209 a year - 4

SerpApi
Free planWebAPIExtension7.4From $25 a month - 5

ImageRights Discovery
Free planWebAPImacOSWindows7.0Free plan - 6
Imagga Visual Search
Free planWebAPILinuxSelf-hosted6.9From $79 a month
