ADAS explores ways to automate the design of agentic systems, as described in its research repository.
Open source
24 alternativesVision agent
The Vision Agent repository is deprecated and directs users to Agentic Document Extraction.
About Vision agent
Vision Agent is an open-source Python library from LandingAI, described as the Visual AI pilot for building vision-enabled apps. Its repository is deprecated, and the repository directs users to Agentic Document Extraction instead. Given a text prompt and an image, the library selects vision models and outputs code intended to run, with a test case it iterates on until the test passes.
Using the library requires Python 3.9 or higher, a VisionAgent API key, an Anthropic API key, and a Google API key. The models that generate code come from Anthropic and Google, so their rate limits and paid tiers apply. The source states that using your own keys avoids the rate limits of LandingAI accounts. Version 1.0.2 and earlier used Anthropic Claude-3.5 and OpenAI o1 and required an OpenAI key instead.
Key features
- Generates runnable vision code from a text prompt and an image
- Selects vision models automatically based on the prompt
- Creates a plan, generated code, and a test case for each prompt
- Iterates on generated code until its test case passes
- Includes a local web app in examples/chat for trying the tool
- Installs as a Python package with uv or pip
Best for: Developers who already use the VisionAgent library or need to review its legacy code, since the repository itself directs new users to Agentic Document Extraction.
Good for
- Open source, with the code available in a public GitHub repository
- Checks generated code against a test case and retries until it passes
- Setup steps, a quickstart, and a sample script are included in the repository
Watch out for
- The repository is deprecated and directs users to Agentic Document Extraction
- Requires separate Anthropic and Google API keys, subject to their rate limits and paid tiers
- Requires Python 3.9 or higher
Vision agent at a glance
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Vision agent alternatives
Tools and sites you could use instead, ranked by how closely they match.
AIlice provides an autonomous, general-purpose AI agent through its open-source repository.
Open source
24 alternatives
This repository provides code for building agents controlled by large language models.
Open source
24 alternatives
The LangChain repository describes an agent engineering platform for building agent based software.
Open source
24 alternatives
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
Open source
24 alternatives
This repository provides an open source framework for self evolving language agents.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
Vision agent FAQ
Is this tool still maintained?
The repository is marked as deprecated. Its README says to use Agentic Document Extraction instead.
Which API keys are needed to run it?
The current setup uses a VisionAgent API key, an Anthropic API key, and a Google API key. Versions 1.0.2 and earlier used an OpenAI API key instead of the Google key.
Who pays for the model usage?
The source says Anthropic and Google each have their own rate limits and paid tiers, and it directs users to their documentation and pricing. It does not state the cost of using the tool.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.