Vision Language Models Python Packages

ameva-runtime

Unified Next-Gen Hardware Orchestration & AI Acceleration Runtime for Mobile & Edge

robot-reel

Review Physical AI with original evidence: compare VLM explanations against recorded robot outcomes, replay SmolVLA failures, and inspect Newton/Genesis simulations offline.

tpips

Code for the paper "The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric."

parse-bench

ParseBench - A Document Parsing Benchmark for AI Agents

docket-idp

Invoice and receipt OCR for Python: extract cited, validated data with local or hosted LLMs

ameva-vulkan-runtime

Unified Cross-Modal Vulkan GPU Acceleration Runtime & HAL for Mobile Android

pixelcue

Local visual-media tagging and image analysis: selectable models, inspectable colour, texture and composition measurements, and REST workflows. Part of DanceFlow.

mstar-ai

A high-performance, universal serving framework for any-to-any models.

mstar-project

A high-performance, universal serving framework for any-to-any models.

langchain-opticparse

Stealth Multimodal Web Scraper & 0-Day Phishing Shield for AI Agents. Alternative to Firecrawl & Crawl4AI with zero-CSS vision extraction, 200 free trial credits, and native LangChain / ElizaOS / MCP support.

tenderness

tenderness is a fast library for synthetic, deterministic document rendering from text and images

opticparse-py

Stealth Multimodal Web Scraper & 0-Day Phishing Shield for AI Agents. Alternative to Firecrawl & Crawl4AI with zero-CSS vision extraction, 200 free trial credits, and native LangChain / ElizaOS / MCP support.

llama-index-tools-opticparse

Stealth Multimodal Web Scraper & 0-Day Phishing Shield for AI Agents. Alternative to Firecrawl & Crawl4AI with zero-CSS vision extraction, 200 free trial credits, and native LangChain / ElizaOS / MCP support.

uijudge-bench

Benchmark for AI judges of web UI quality: verified ground truth for accessibility, layout, and design-quality judgment

goldeneye

GoldenEye is a library of geospatial vision-language models -- run any geospatial VLM in three lines of code

relsim

🍑 relsim: Relational Visual Similarity | pip install relsim 🌍 (CVPR 2026)