# landing-ai/vision-agent

This tool has been deprecated. Use Agentic Document Extraction instead.

Repository: https://github.com/landing-ai/vision-agent
Canonical: https://ross.abutalabs.com/products/vision-agent
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-01-29T06:23:55+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 64, release rhythm 35, longevity 66
- inputs: {"age_days": 933, "days_push": 216, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5296, forks 600 (observed 2026-08-28T04:09:15.237487+00:00)

## What it is
VisionAgent is a Python library from LandingAI that takes a natural-language prompt plus an image or video and automatically selects appropriate vision models, generating ready-to-run vision code. It has been deprecated in favor of Agentic Document Extraction.

## Use cases
- generate computer vision code from a prompt and image
- build visual AI apps quickly
- automatically pick the right vision model for a task
- prototype vision pipelines without writing code
- process images and videos with AI agents

## When to choose
- you want to rapidly prototype vision applications from natural-language prompts
- you need generated, runnable vision code rather than manual model selection

## When to avoid
- starting a new project, since the tool is deprecated in favor of Agentic Document Extraction
- you need a fully self-contained solution, since it requires Anthropic and Google API keys
- you need long-term support or updates

## Facets
- artifact type: library
- maturity: abandoned
- function: agent-framework, computer-vision, image-processing, machine-learning, llm-inference
- domain: computer-vision, artificial-intelligence, image-processing, developer-tools
- platform: python, cross-platform
- tags: visual-ai, vision-models, code-generation, deprecated, landing-ai, video-processing, ai-agents

## Member repositories
- landing-ai/vision-agent (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:15.237487+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:59:10.767026+00:00, confidence not recorded.
  - readme: https://github.com/landing-ai/vision-agent (fetched 2026-08-28T04:09:15.237487+00:00, sha 0bdf33e42633)
- Data as of 2026-08-30T08:39:29.467469+00:00.