Jev AgentA source-verified directory of 487 Jev projects — browser agents, model routers, SDKs and MCP servers — each one showing the exact decision it hands to Jev. Curated by the Awesome Jev community, mirrored here under MIT.
Give Jev the current state and a few options. Get the Agent’s next step.
Core call · setup in the full example
const nextStep = choice("What next?", { login: null, askUser: null, retry: null });
const { answers } = await client.systemOne({ state: "Login form is ready", questions: { nextStep } });
console.log(answers.nextStep.choice);Node.js 20+ · Set TYPESAFE_API_KEY on your server. This page shows code and makes no model requests.
Cua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.
Reads DOM or supported visual-region descriptions and returns a supplied candidate action ID.
Provides Python and TypeScript loops with separate offline and live checks.
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
Chooses an action and its matching DOM element in one request; a text model generates input text.
Separates UI choices, text generation, and browser execution so each step can be inspected.
An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.
Keeps the full UI tree out of the main Agent context while exposing the selected action.
Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.
Selects the next step from deterministically extracted controls and actions before desktop execution.
Separates screen reading, action selection, and text generation.
A Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act.
Chooses targets and actions and assesses completion and risk; local policy controls execution or confirmation.
Uses text candidates and starts with a dry run by default.
An omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.
Chooses controls and checks completion or blockage before the test runner operates the UI.
Adds choices grounded in current UI state to mobile testing.
A Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.
Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.
Separates repetitive page choices into decision steps while reusing the browser connection.
Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.
Chooses apps, controls and next actions from phone state; Mobilerun executes them.
Records action traces and request latency for inspection.
Drives a browser from a task and URL, returning the final page, screenshot and action trace.
Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.
Records proposed actions, execution and stop reasons for inspection.
Controls a Playwright browser by sending incremental speech transcripts to Jev.
Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.
Shows probabilities, actions and request timing during voice interaction.
Voice and typed computer use for macOS. You say what you want. Jev picks the next on-screen action. macOS performs it. No screenshots: the app reads the screen through the Accessibility tree.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
An experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.
Batches element text, labels, and link information into Noul questions and applies a threshold.
Shows how semantic judgments can be connected to concrete page elements.
A browser library, CLI and MCP server where the caller supplies goals and text while Jev selects actions.
Chooses elements, actions and values, and assesses completion, errors and irreversible steps.
Separates browser-action loops from caller planning and returns status and traces.
A native macOS automation loop using local OCR and accessibility information with Jev action selection.
Jev selects controls or groups from locally observed candidates; coordinates and input execution stay on the Mac.
Makes candidate controls and execution checks inspectable, including Finder workflows.
A Manifest V3 Chrome port of jev-ultrafast: Jev picks the operation and DOM element in one request per step; a small chat model fills TYPE_TEXT.
Chooses CLICK, TYPE_TEXT, SELECT, SCROLL_DOWN, SCROLL_UP, PRESS_ENTER, WAIT, DONE, or BLOCKED and the matching DOM target in one request; PRESS_ENTER is a separate key control. Separate yes/no checks cover goal completion and a stuck loop.
Runs in the user’s own tabs without screenshots, and keeps the action, target, and typed string inspectable.
Open `test/sample-form.html` in the browser, configure the extension, and click **Autofill page**.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A browser Agent for ego lite that numbers actionable elements for Jev to choose the next step.
Jev selects an operation and target in one request; a separate helper handles free-form text when needed.
Offers observation, suggestions and execution, while uploads and dialogs still require other browser tools.
Connects Agents to a browser over MCP, using Jev to choose page actions with confirmation gates for actions such as payment or deletion.
Selects actions from current page controls and assesses risk and irreversibility.
Combines automated page actions with user confirmation in one workflow.
An MCP server and skill adding Jev decisions to Aside browser Agents.
The Agent supplies action candidates; Jev picks an ID, then the Agent executes and verifies it through Aside.
Keeps choices within an application-owned action table while requiring separate outcome verification.
A macOS desktop clerk that books supplier invoices: Jev picks each click from a closed action list; a deep model only rewrites the playbook.
POSTs https://api.typesafe.ai/v1/systemone as jev-latest with a closed action Choice each step.
Screen actions follow Jev's closed choices. Author demo numbers were not retested here. GitHub SPDX is empty; the LICENSE file is MIT.
Playwright browser automation with Jev decisions through a shared CLI, MCP server and TypeScript SDK.
Jev chooses actions, matches form fields or extracts structured content from page observations; Playwright executes.
Supports persistent sessions and UI readback, which does not by itself prove database persistence.
This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
`jev-mobile` accepts a high-level task, persists it in SQLite, and lets one durable worker execute **observe → normalize → decide → mutate → verify** against a USB-connected Android device. Jev receives concise semantics and technically valid actions; it never generates coordinates, MCP calls, or arbitrary code.
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
A Go-based macOS controller that asks Jev to choose controls and actions from the accessibility tree.
Uses window state to select an action, target, text-input need, and completion status.
Grounds candidate controls in UI snapshots so choices can be inspected.
A community-maintained directory and radar for Jev, highlighting open-source projects with verified code and clear decision architectures.
Jev is TypeSafe's decision model. This directory groups projects by how they use choices, scores and probability judgements, with implementation links to help you assess fit for your own task.
TypeSafe ↗We prioritize open-source projects with clear Jev implementation evidence. Repositories without verifiable source code are excluded from the main directory.
Directory data and design from Awesome Jev by logicrw, used under the MIT License.
