Post Β· Agents & browsers
Trust the ordering, not the confidence number
Where to place the decision model inside an agent harness.
Open x.com βππ‘ππ«π πππ― πππ₯π¨π§π π¬ π’π§ ππ§ ππ ππ§π πππ«π§ππ¬π¬ (ππ¨π π ππ¨πππ₯ ππ°ππ©)
Your agent harness needs a decision model. Where you place it depends on one brutal fact: Jev's ordering is trustworthy. Its confidence numbers are not.
Most placement guides https://t.co/1ObJtv9nus
The decision Jev makes
Pick the next click, field or navigation from the legal actions on screen.
Where it fits
Browser agents need to choose an action on every step. With Jev each step is a choice from the actions actually available on the page, which keeps agents fast and on the rails. All 299 agents & browsers projects β
Related projects
Agents & browsersdocent_chrome_pluginA pluign for TypeSafe AI's Jev.GitHub Β· β
2 Β· yepher
Agents & browsers@sideform/browser-agentGoal-driven browser agent library in TypeScript (controller, step policy, browse_task loop) whose step policy uses a System One decision client suchβ¦GitHub Β· dan-rozhkov
Agents & browsersLathAgent loops that pay for model calls over a Tempo payment channel with every call recorded on Solana; a separate TypeSafe Jev decision answersβ¦GitHub Β· lath-agents
Agents & browsersvoice-browsermacOS command bar that drives Chromium, Dia, Arc or Chrome from plain English; TypeSafe Jev (or SubQ Snap) picks clicks and targets for fast singleβ¦GitHub Β· ken-code-wq
Agents & browsersjevdohsom (Harness for System One Models, repository jevdo) lets Jev operate a bash shell by walking a strict-allowlist decision tree of commands,β¦GitHub Β· β
4 Β· gi-dellav
Agents & browserskureksistantAutonomous, sub-second personal AI assistant for Arch Linux (Hyprland) & macOS.GitHub Β· β
1 Β· nodaysidle