VisionTasker

An Android automation implementation that translates screenshot-based UI understanding into language descriptions for step-by-step LLM planning and action execution.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

What is this resource?

Resource type

Agents

Environment

android

Topics

mobile-navigation, screen-understanding, planning

Record publication date

Not recorded

Evidence retrieved

2026-10-17T11:20:18Z

Resource ID

github:akimotoayako/visiontasker

What licenses are recorded?

Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.

Code

GPL-3.0 (Repository GNU GPL version 3 license; pretrained models and linked data retain separate terms.)

Data

Not recorded

Document

Not recorded

Weights

Not recorded

License review notes

• Code: Repository GNU GPL version 3 license; pretrained models and linked data retain separate terms. Source 1

Recorded specifications

availability

Public Android automation source and setup instructions; external models/services required.

repository revision

d31b50e98bde28c0d1cfbc7d7ee2528d10b3fbb0

Explore related topics

Scope and limitations

The official lowercase readme.md and source tree expose automatic and step-by-step entry points. The documented setup uses a Windows host and an Android phone connected through ADB; it also requires separately obtained detection/CLIP models and model/OCR services. GPL-3.0 is recorded for the code only. External model download links were not used to infer weight licenses or verify a separate checkpoint release.

Related resources

• documented by: VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning

Primary evidence and verification

Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.

1. editorial primary review

   Retrieved 2026-10-17T11:20:18Z. Supports: name, kind, summary, environments, topics, scope, notes, relations.

   Content fingerprint

   816981b343628c53188fd27041d62f52854fcfe83c976a125b84545f5e010274
2. editorial primary review

   Retrieved 2026-10-17T11:18:23Z. Supports: identity.

   Content fingerprint

   94d8e95d302160e3c581015267dcfbb9f61c41ad1f04e470fcd71f5ee1ffa25d
3. editorial primary review

   Retrieved 2026-10-17T11:19:48Z. Supports: release_status, details.repository_revision.

   Content fingerprint

   54a1c08d44e0ad1d60bee57e3db2842518e014db3be8b08362e484315f3a6a6f
4. editorial primary review

   Retrieved 2026-10-17T11:23:03Z. Supports: licenses.code.

   Content fingerprint

   3972dc9744f6499f0f9b2dbf76696f2ae7ad8af9b23dde66d6af86c9dfb36986

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.