GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
Decision brief
Unverified catalog guidance: autotab-starter, licensed under MIT, serves as a Python framework for creating custom AI agents dedicated to browser automation to execute real-world tasks.
Good fit when
- Unverified catalog guidance: When you specifically need agent-oriented solutions that tightly couple with web browser activities and require fine-tuned automation on the internet.
- Unverified catalog guidance: In scenarios where your project is open source or requires an MIT license, offering flexibility in integration without restrictive terms.
Avoid when
- Unverified catalog guidance: If your project demands proprietary licensing since restraints associated with closed-source tools cannot be met by autotab-starter's MIT license terms.
- Unverified catalog guidance: When the focus of automation does not align closely with web browsers but requires control over other application types or direct system functionalities.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (1012d since push)
- As of Sep 20, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 20, 2026
- Security (OSV)
- No lockfile
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
Package installation is not established from the available documentation. Check the source repository for setup instructions.
git clone https://github.com/planetary-computers/autotab-starterSource repositorySimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
autotab-starter offers a Python-based framework to develop AI agents tailored for automation in web browsers.
Capability facts
- Languages
- python
Source: github.language · Sep 20, 2026
Categories
Tags
README
Installation See the quickstart above (Steps 1 and 2). Running installs all the dependencies as well as the local package which enables the and commands.
For agents
This page has a .md twin and JSON over the API.