Vision Python Packages

flow-vis

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

98K 457 57

pybv

A lightweight I/O utility for the BrainVision data format, written in Python.

36K 24 13

unitxt

🦄 Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data for end-to-end AI benchmarking

22K 215 69

power-grid-model-io

Conversion tool for various grid data formats to power-grid-model

15K 30 19

torch-pruning

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

14K 3K 387

abstractframework

Write once. Generate everything. A modular, open-source ecosystem for building durable, observable, multimodal AI systems. Text, voice, image, video, music — one unified interface, any provider, any model, local or cloud.

12K 4 0

achatbot

An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.

12K 90 18

potato-annotation

potato: the portable annotation tool

5K 429 76

caer

High-performance Vision library in Python. Scale your research, not boilerplate.

4K 819 111

abstractmemory

3K 4 0

mantis-vl

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

3K 241 22

nybls

Low cost, iterative video watching for AI agents. Transcript first, then only the frames it asks for, with receipts.

3K 1 1

bnnr

XAI-driven augmentation & diagnostics for PyTorch vision - find model failures, fix with saliency-guided augmentation (ICD/AICD), prove with auditable reports.

3K 36 11

bridgenode-llm

BridgeNode — x402 pay-per-request AI inference. Python SDK.

2K 1 0

oximedia

OxiMedia is the Sovereign Media Framework - A patent-free, memory-safe multimedia processing library written in pure Rust. Pure Rust reconstruction of both FFmpeg (multimedia processing) and OpenCV (computer vision) — unified in a single cohesive framework.

2K 262 26

effero

Effero is a modular runtime for building agentic AI systems.

2K 2 1

kwcapture

Fast screen capture for KDE Plasma on Wayland: ~40 fps at 1440p via KWin ScreenShot2 D-Bus, zero-copy shared-memory frames, Python API + CLI

2K 0 0

codex-deepseek-vision

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

2K 8 0

projectdavid-platform

A single pip installed package will orchestrate a production ready instance of the AI stack in any environment

2K 1 0

annolid

An annotation and instance segmentation-based multi-object tracking and behavior analysis package.

1K 59 11

pixelrag

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

1K 10K 899

slip

a Simple Library for Image Processing

1K 4 3

kvm-pilot

Smart hands for your AI agents — write-capable, multi-plane (KVM + BMC + SSH) MCP server for bare-metal control (PiKVM/GLKVM, Redfish/IPMI BMCs): gated, verified, audited. Beta: seeking hardware reports.

1K 7 3

bridgenode-cli

BridgeNode — x402 pay-per-request AI inference. Python SDK.

1K 1 0