# eze-is/web-access

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/eze-is-web-access).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

9,358 stars · 659 forks · JavaScript

## Links

- GitHub: https://github.com/eze-is/web-access
- awesome-repositories: https://awesome-repositories.com/repository/eze-is-web-access.md

## Description

Web Access is a skill for local AI coding agents that gives them web access by driving a real Chromium-based browser. It connects to the browser the user already uses every day through its debugging port and a local proxy, so agents inherit existing logins and can work on dynamic pages, open background tabs, click, fill forms, scroll, upload files, and capture screenshots.

Beyond browser control, it routes each task to the cheapest sufficient channel: search, plain page fetch, raw retrieval, Markdown conversion through a third-party converter (which loses some information), or full browser control when login or dynamic rendering is needed. Multi-target research can be split across sub-agents that each work in their own isolated tab over one shared connection, keeping fetched content out of the main context. The skill also reads and clicks inside cross-site and cross-process iframes, and it keeps per-site notes such as URL patterns and known pitfalls so later sessions can reuse them.

The local proxy reuses a healthy existing connection and reconnects after disconnects, which avoids repeated browser authorization prompts. It closes tabs it created after an idle period and leaves the user's own tabs alone. It supports Chrome, Edge, Brave, Arc, and other Chromium browsers via a configured data directory, and it will not silently fall back to a different browser. It can also search local bookmarks and history to find previously visited pages, including internal systems. Preferences and site notes are stored in a home-directory folder outside the install, with a one-time non-destructive migration from older locations, so upgrades do not overwrite them.

## Tags

### Artificial Intelligence & ML

- [Browser Automation Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/browser-automation-agents.md) — Gives local AI coding agents web access by driving a real Chromium browser with reused logins for dynamic pages and interactive actions.
- [Web Research Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/ai-agents/research-agents/web-research-agents.md) — Splits multi-target research across sub-agents that each work in isolated tabs over one shared connection, then merges findings.
- [Site Experience Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-knowledge-bases/site-experience-stores.md) — Keeps per-site notes such as URL patterns and known pitfalls in a persistent home-directory folder that later sessions reuse and upgrades never overwrite.
- [Web Browsing Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/agent-and-tool-integrations/web-browsing-tools.md) — Picks among search, page fetch, curl, Markdown conversion, and browser control per task, combining them to reach web content efficiently. ([source](https://github.com/eze-is/web-access#readme))
- [Parallel Research Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/web-research-agents/parallel-research-orchestration.md) — Splits multi-target research across sub-agents that each use their own isolated browser tab over one shared connection, keeping fetched content out of the main context.

### Networking & Communication

- [Local Browser Proxies](https://awesome-repositories.com/f/networking-communication/proxy-servers/local-browser-proxies.md) — Connects through a local proxy to the user's everyday Chromium browser, inheriting logged-in sessions and using background tabs that close when finished. ([source](https://github.com/eze-is/web-access/blob/main/SKILL.md))
- [Browser Tab Control Proxies](https://awesome-repositories.com/f/networking-communication/proxy-servers/tool-execution-proxies/devtools-proxies/browser-tab-control-proxies.md) — Provides a local HTTP proxy over the Chrome DevTools Protocol so agents can open, navigate, script, and screenshot tabs through simple requests.
- [Session-Sharing HTTP Daemons](https://awesome-repositories.com/f/networking-communication/http-proxies/websocket-tunneled/cdp-websocket-tunnels/session-sharing-http-daemons.md) — Runs a long-lived local daemon that holds one authorized browser connection and exposes it as a simple HTTP API for many callers.

### Web Development

- [Browser Automation](https://awesome-repositories.com/f/web-development/browser-automation.md) — Connects to the user's existing Chromium-based browser through its debugging port so tasks run in the real logged-in browser. ([source](https://github.com/eze-is/web-access/blob/main/AGENTS.md))
- [API and Browser Channel Routing](https://awesome-repositories.com/f/web-development/browser-to-ai-api-routing/api-and-browser-channel-routing.md) — Routes each web task to the cheapest sufficient channel, from search and plain fetch up to full browser control when login or rendering is needed.
- [Browser Form Automation](https://awesome-repositories.com/f/web-development/form-data-support/form-data-submission/browser-form-automation.md) — Automates the user's daily browser with existing logins to open tabs, click, fill forms, scroll, upload files, and take screenshots.
- [Browser Control APIs](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-control-protocols/browser-control-apis.md) — Exposes a local HTTP interface over a browser WebSocket connection to open, navigate, and manage tabs, closing idle tabs automatically. ([source](https://github.com/eze-is/web-access#readme))
- [Chrome DevTools Protocols](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-control-protocols/chrome-devtools-protocols.md) — Connects to Chromium browsers through their debugging port and a local proxy so agents drive tabs, frames, and scripts over CDP.
- [Browser Interaction Actions](https://awesome-repositories.com/f/web-development/web-automation-scraping/browser-interaction-primitives/browser-interaction-actions.md) — Drives the user's everyday logged-in Chromium browser through a local proxy to handle dynamic pages and interactive actions. ([source](https://github.com/eze-is/web-access#readme))
- [Multi-Channel Retrieval Routers](https://awesome-repositories.com/f/web-development/web-page-retrievers/multi-channel-retrieval-routers.md) — Routes each web task to the cheapest sufficient channel, from search and plain fetch to Markdown conversion or full logged-in browser control.
- [Auto-Reconnecting Connections](https://awesome-repositories.com/f/web-development/browser-integration-utilities/browser-extension-development/browser-extensions/agent-browser-controls/existing-session-reuse/auto-reconnecting-connections.md) — Runs a background proxy that reuses a healthy browser connection and reconnects after disconnects, avoiding repeated browser authorization prompts. ([source](https://github.com/eze-is/web-access/blob/main/AGENTS.md))
- [Per-Agent Tab Isolation](https://awesome-repositories.com/f/web-development/browser-integration-utilities/browser-session-management/tab-management/tab-openers/per-agent-tab-isolation.md) — Gives each worker agent its own background tab over one shared connection, keeping parallel tasks separated and fetched content out of the main context.
- [Web Page Retrievers](https://awesome-repositories.com/f/web-development/web-page-retrievers.md) — Chooses between search, targeted page fetch, raw HTML retrieval, and a live browser depending on URL knowledge and login needs. ([source](https://github.com/eze-is/web-access/blob/main/SKILL.md))

### Part of an Awesome List

- [Search and Web](https://awesome-repositories.com/f/awesome-lists/ai/search-and-web.md) — Selects automatically among search, fetch, curl, reader proxies, and browser control to complete a web task. ([source](https://github.com/eze-is/web-access/blob/main/README.md))

### Content Management & Publishing

- [Site-Specific Memory](https://awesome-repositories.com/f/content-management-publishing/documentation-knowledge-management/knowledge-bases/execution-knowledge-stores/site-specific-memory.md) — Stores per-domain notes such as URL patterns and known pitfalls in a persistent folder that later sessions reuse and upgrades preserve.

### Development Tools & Productivity

- [Sub-Problem Parallelization](https://awesome-repositories.com/f/development-tools-productivity/parallel-execution/custom-parallel-task-execution/parallel-task-orchestrators/concurrent-agent-messaging/sub-problem-parallelization.md) — Splits independent research targets across sub-agents that each use their own browser tabs, keeping fetched content out of the main context. ([source](https://github.com/eze-is/web-access/blob/main/SKILL.md))

### Security & Cryptography

- [Iframe Navigation and Targeting](https://awesome-repositories.com/f/security-cryptography/iframe-sandboxing/iframe-navigation-and-targeting.md) — Reads and clicks inside cross-site and cross-process iframes by attaching to child sessions and descending nested frames by coordinates. ([source](https://github.com/eze-is/web-access/blob/main/references/cdp-api.md))
- [Page Interaction Actions](https://awesome-repositories.com/f/security-cryptography/iframe-sandboxing/iframe-navigation-and-targeting/page-interaction-actions.md) — Queries elements, clicks, scrolls, fills forms, and uploads files, choosing scripted or real mouse actions to avoid anti-bot blocks. ([source](https://github.com/eze-is/web-access/blob/main/SKILL.md))

### User Interface & Experience

- [Cross-Frame Interaction Synchronization](https://awesome-repositories.com/f/user-interface-experience/cross-frame-interaction-synchronization.md) — Reads and clicks content inside cross-site, nested, and cross-process iframes that ordinary page scripts cannot reach.
