Discover the Best AI Tools

Reranks Google organic search results using Jev and configurable rules, with restoration of the original order. Uses result titles, URLs and snippets rather than full pages; currently supports www.google.com and requires a paid API key.

A Node MCP browser server using Playwright and Jev to jointly choose actions, elements and supplied literal text. Requires Chromium and model access; callers provide text values, and probabilistic decisions are not a security boundary.

Proxies Playwright MCP with Jev-based page triage, content pruning and risk checks. Without an API key it passes requests through; model judgments are not a security guarantee or authorization mechanism.

A Python local web UI for browser automation: Jev selects bounded actions while a separate text model supplies field values. Supports manual and automatic steps with traces; requires model credentials.

PlayJev extends an existing Playwright page with natural-language actions, form filling and state checks driven by Jev. It keeps the underlying Playwright API and chooses from observed controls. Chromium/CDP and a TypeSafe key are required. The API is experimental; small live smoke tests do not establish broad browser reliability.

Vinilana’s Jev Browser uses OpenRouter to plan subgoals and generate field text, Jev to select DOM actions, and Playwright to execute them with local reports. It needs provider keys; supplied values can reach OpenRouter and page context reaches TypeSafe. Traces may contain private data, and prompt-based restrictions are not a security barrier.

Fastbrowse combines Jev choices, a text-model planner and browser execution to return cited answers or structured results. It supports cloud, local and attached browsers with provider credentials and spending controls. This is pre-alpha: evidence citations and sensitive-action guards are useful checks, not guarantees against misleading pages or incorrect completion.

Jev Agent Browser delegates bounded browsing to Jev and the external agent-browser executable. A parent supplies the goal and finite input values; ambiguity, repetition or missing values return a handoff rather than invented input. It needs TypeSafe access and the peer browser tool, and does not include a general text-generating planner.

Jev Browser Bridge runs a Jev action loop against local or hosted CDP browsers, including engines without rendered screenshots. It reads DOM structure and retrieves relevant text; typing can use a separate text model. Browser/CDP compatibility and provider credentials are required, and bounded choices do not establish correct task completion.

A TypeScript agent drives ego lite through indexed page controls and optional Jev decisions, with a text model for generated input; it needs macOS, ego lite and provider keys for model modes, while uploads, frames, canvas and pop-up tabs remain outside its MVP.

A Python MCP server runs browser goals as a server-side decision loop with page-state checks and reusable macros; it needs Chromium and model access for Jev decisions, while basic observation and recorded macro replay can work without model calls.

Jevry is a source-preview desktop browser combining Jev action selection, a separate text model and visible Chromium execution. It requires Node, TypeSafe and a text-model connection, with external inference costs. Website support varies; uploads, downloads and some cross-origin/custom controls are unsupported or unverified, and local storage does not mean offline inference.

Fast Browser Use runs local Qwen models through MLX or PyTorch to choose observed browser controls and generate field text when needed. It requires downloaded model weights and suitable hardware; live sites still need networking. Bounded choices reduce invented selectors but do not guarantee correct actions, and this is not an official local Jev model.

An executable browser bridge delegates navigation and controls to Jev while Codex handles typing, visual interpretation and final verification; it needs Node.js 22+, an existing Codex Computer Use connection and TypeSafe or OpenRouter access, and sends page text to that provider.

A CLI and Chrome-family extension let agents navigate, inspect pages, capture network traffic and operate existing browser sessions; installation needs the extension and native host, and access to AI websites uses the user’s existing logins and service limits.

Ghostfox combines a Firefox-derived browser engine with a Rust MCP runtime for agent-controlled browsing, session management and identity profiles. It is self-hosted and requires the browser engine and runtime. The engine and runtime have different licenses; website access and anti-detection success are not guaranteed.

Chromium extension and local Node host for controlling real tabs through side-panel chat or a DevTools terminal. Uses the GitHub Copilot SDK and requires Copilot access. Page content read by the agent is sent to Copilot; it is designed for a human-operated browser workflow.

Tool connecting agent command-line interfaces with websites through APIs.

Webcmd is described as a self-learning browser for AI agents.

A browser extension for developing and debugging browser-based applications with AI assistance.

A Rust-based browser with AI capabilities for developers.