Vision AI agent tools

Sparrow

NewvisionOpen source

Open-source tool for structured data extraction from documents and images with ML, LLMs and vision LLMs, plus agentic workflows.

Added Oct 18, 2026

Viso Now

NewvisionFreemium

Describe what a camera should watch for in plain language and it builds a live vision app with detection logic, alerts and integrations, no datasets or training needed.

Added Oct 17, 2026

Ultralytics Agents

NewvisionFreemium

Visual canvas in Ultralytics Platform that chains YOLO models, vision-language models, conditions and actions like Slack alerts, plus official agent skills that let coding agents train, tune and export YOLO models.

Added Oct 17, 2026

NVIDIA TAO Agent Skills

NewvisionOpen source

NVIDIA's vision-model post-training toolkit, now packaged as agent skills so Claude Code or Codex can fine-tune, optimize and export vision foundation models from plain-English prompts.

Added Oct 17, 2026

NVIDIA VSS Blueprint

NewvisionOpen source

NVIDIA reference blueprint for video AI agents that search, summarize, answer questions and raise alerts over live or recorded video, with agent skills that assemble deployments from one prompt.

Added Oct 17, 2026

Autodistill

NewvisionOpen source

Roboflow's open-source library that uses large foundation models to auto-label images and then trains small, deployable detection or classification models with no manual labeling.

Added Oct 17, 2026

FiftyOne MCP Server

NewvisionOpen source

Voxel51's MCP server and skills that let AI agents load, explore, curate and evaluate computer vision datasets and run FiftyOne operators and the App from natural language.

Added Oct 17, 2026

Encord Agents

NewvisionPaid

Encord's agents that plug foundation models or your own models into labeling workflows to pre-label, segment, track, route and QA image, video and multimodal data, with a no-code catalog and an open-source SDK.

Added Oct 17, 2026

Encord Merlin

NewvisionPaid

Encord's beta MCP server and in-app agent that creates annotation projects, ontologies and workflows and reports label-quality analytics from Claude, Codex or other AI tools.

Added Oct 17, 2026

Label Studio MCP Server

NewvisionOpen source

HumanSignal's MCP server that lets AI assistants create Label Studio labeling projects, import tasks, read annotations and add model predictions.

Added Oct 17, 2026

CVAT AI Agents

NewvisionFreemium

CVAT feature that runs your own detection, segmentation or tracking model as an agent on your infrastructure and feeds its auto-annotations back into CVAT tasks.

Added Oct 17, 2026

TwelveLabs Jockey MCP

NewvisionFreemium

TwelveLabs' hosted MCP server for Jockey, a video-understanding agent that searches, tracks entities and answers questions across your videos and images with clip citations.

Added Oct 17, 2026

Groundlight

NewvisionSee site

Turns any camera into a vision sensor: you ask a yes/no question in plain English and Groundlight builds and tunes the model, backed by human review, with edge deployment.

Added Oct 17, 2026

EyePop.ai

NewvisionFreemium

SDK-first vision platform where you define what to detect and it builds detection, tracking, OCR and VLM pipelines, with a Video Agent and agent skills, deployable to cloud, edge or on-prem.

Added Oct 17, 2026

Telekinesis Agentic Skill Library

NewvisionFreemium

Python library of 250+ perception, vision and robotics skills plus a Physical AI agent that turns natural-language prompts into reviewable robot code.

Added Oct 17, 2026

Bubbaloop

NewvisionOpen source

Kornia's open-source single-binary agent runtime with an MCP server that orchestrates cameras, sensors and robots on Jetson, Raspberry Pi or Linux through chat.

Added Oct 17, 2026

ImageSorcery MCP

NewvisionOpen source

Local MCP server that gives AI assistants object detection, OCR, cropping, background removal and drawing tools, running computer vision models on your own machine.

Added Oct 17, 2026

YRIKKA Text-to-Model

NewvisionEnterprise

YRIKKA's ORION workflow that turns a plain-language mission description and a few unlabeled images into generated training data, candidate models and an evaluated, selected vision model.

Added Oct 17, 2026

Valossa Assistant MCP

NewvisionFreemium

EU-based video AI MCP server that lets Claude and other agents upload and search videos and pull transcripts, visual scenes, soundbites and ready-made clips.

Added Oct 17, 2026

Picsellia MCP Server

NewvisionPaid

Official MCP server for Picsellia's computer vision MLOps platform, giving AI assistants access to datasets, experiments, models, deployments and monitoring.

Added Oct 17, 2026

Roboflow Agent

visionPaid

Computer-vision agent that picks models and builds/deploys vision apps; plugs into Claude Code, Codex, Cursor via MCP.

Added Oct 14, 2026