Home/Computer Vision/llavavision

llavavision

lxe/llavavision

A simple Be My Eyes web app with llama.cpp/llava backend

GitHub

GraphCanon updated 3w · GitHub synced 3w

496 stars34 forksLast push 2y JavaScript

Decision brief

llavavision is an experimental web application that provides users with computer-vision capabilities powered by llama.cpp/llava backend, allowing local processing of images and video streams.

Good fit when

When you need a lightweight, locally deployed AI solution for basic vision tasks that can operate on moderate hardware resources (~5 GB RAM)
For developers interested in experimenting with integrating computer-vision into web interfaces without relying solely on cloud-based models

Avoid when

If your application requires high-performance computations or large-scale data processing beyond low to mid-tier hardware capabilities
In scenarios where strict real-time performance is critical, as llavavision may not offer the necessary speed due to its computational dependencies on local resources

Observed Jul 17, 2026 · Source: enrich:decision_facts

llavavision alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (976d since push); As of 3w
Provenance: Not a fork · Personal account; As of 3w
Security (OSV): No criticals; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install llavavision

npm

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

open-webui

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

149k★

Open-LLM-VTuber

Voice interaction with LLMs and Live2D visuals

13k★

lmms-eval

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

4.4k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Developed in JavaScript, this repository houses a computer-vision-oriented AI application that operates via a web interface and leverages llama.cpp for its computations.

Capability facts

Deploy: Self-host
Source: dockerfile:Dockerfile · Jul 31, 2026
Docker: Dockerfile present
Source: dockerfile:Dockerfile · Jul 31, 2026
Languages: javascript
Source: github.language · Jul 31, 2026

README

Getting Started

You will need a machine with about ~5 GB of RAM/VRAM for the q4_k version.

For agents

This page has a .md twin and JSON over the API.

/tools/lxe-llavavision.md GET /api/graphcanon/tools/lxe-llavavision GET /api/graphcanon/graph?tool=lxe-llavavision