Footwork
A verified browser agent: a cheap Jev guard (evidence-checked completions, a destructive gate) in front of any LLM browser driver, with Jev taking the mechanical steps in dual mode. Built on browser-use; every number pre-registered and measured.
How it uses Jev
A verified computer-use agent, for the browser and for native macOS apps. Footwork puts a cheap, calibrated guard from TypeSafe Jev in front of whoever drives: every claimed completion is checked against observed state and the trajectory before it counts, every irreversible action passes a gate, and every action comes back with a receipt saying what visibly changed. On top of that guard, Jev can also take the fast,…
Highlights
- The guard is the product. Zero false completions on every split and run, on these predicates, at
- Jev acting saves driver work, not money yet. Dual makes 23 to 29% fewer driver requests than the
- System 2 delegating bounded subgoals to Jev did not pay in three measurements
- Declaring the contract to the driver did not pay ( Q11 ): model
- The arbiter's calibration transfers from DOM menus to accessibility-tree menus
- A session runs beside a person without taking their work, input or focus
Getting started
To run the agent or the evals you need a TypeSafe key ( TYPESAFE API KEY ) and a System 2 key ( MODEL API KEY for the Meta Model API, or wire another provider in evals/runner.py ):
- Languages
- Python 90% · Rust 8% · HTML 2% · Shell 1%
- License
- MIT
- Last activity
- Sep 2026
- Added
- 2026-09-23
- Stars at snapshot
- 1
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.
