# E2LLM E2LLM connects the AI you already use to the browser session you are already signed in to. It reads the live page as structure, supplies explicit browser actions, and verifies writes by reading the page again. Site: https://e2llm.com/ Company: S2 Tikshuv Ltd, Israel Contact: info@e2llm.com ## Start - [Connect your AI](https://e2llm.com/start/): anonymous three-step setup wizard for choosing a browser and AI client, installing the MCP extension, connecting it, and proving the connection on a real page. - https://e2llm.com/downloads/ permanently redirects to the setup wizard. Supported browsers shown by the wizard: Chrome, Edge, Firefox, Arc, and Comet. Safari is not supported. AI clients shown by the wizard: ChatGPT, Claude, Grok, Perplexity, Mistral, Claude Code, Codex, Kimi, Copilot, and other MCP-compatible clients. Copilot is marked tested. ## Product - [Homepage](https://e2llm.com/): product claim, browser-perception approach, enterprise deployment, and pricing. - [E2LLM skill](https://e2llm.com/SKILL.md): live-browser operating instructions for AI agents. Install the `e2llm` and `sifr` skills with `npx skills add e2llm/e2llm-sifr`. - [Developers](https://e2llm.com/developers/): developer entry point and setup resources. - [Documentation](https://e2llm.com/docs/): setup, MCP tools, and use cases. - [Setup guide](https://e2llm.com/docs/setup/): detailed installation and client configuration. - [MCP tools](https://e2llm.com/docs/mcp-tools/): tool reference. - [Use cases](https://e2llm.com/docs/use-cases/): worked browser-perception examples. - [Connect Cursor](https://e2llm.com/docs/connect/cursor/): ready-made instructions for connecting Cursor to E2LLM's remote browser MCP server, verifying the tools, and debugging a rendered application beside its source code. - [Connect VS Code Copilot](https://e2llm.com/docs/connect/vscode-copilot/): configure remote browser MCP tools and debug accessibility against the rendered application. - [Connect Windsurf](https://e2llm.com/docs/connect/windsurf/): configure Cascade and repair responsive layouts using live viewport evidence. - [Connect Zed](https://e2llm.com/docs/connect/zed/): add E2LLM as a remote context server and trace rendered focus data to source. - [Connect Warp](https://e2llm.com/docs/connect/warp/): connect Warp Agent and correlate terminal deployment evidence with the rendered service. - [Connect Raycast](https://e2llm.com/docs/connect/raycast/): connect Raycast AI and build sourced comparisons from open browser tabs. - [SiFR format](https://e2llm.com/sifr/): structured capture format and reference implementation. - [Runtime Snapshots](https://e2llm.com/snapshots/): browser-perception engineering series. - [Structured browser perception](https://e2llm.com/structured-browser-perception/): the architectural approach. ## Browser-agent guides - [Give Claude Code Browser Access with E2LLM](https://e2llm.com/give-claude-code-browser-access/): Give Claude Code browser access to open tabs, authenticated pages and local apps through E2LLM, then verify the live connection with list_tabs. - [Reduce Browser Agent Token Usage with Structured Page State](https://e2llm.com/reduce-browser-agent-token-usage/): Reduce browser agent token usage by capturing structured page state once, querying focused details, reading diffs and recapturing only when state changes. - [Browser Agent Missing Accessibility Tree Elements: Causes and Fixes](https://e2llm.com/browser-agent-cannot-see-accessibility-tree-elements/): Learn why browser agents miss accessibility tree elements and how rendered structure, layout, occlusion and fresh capture recover the target. - [Accessibility Tree vs Screenshot](https://e2llm.com/accessibility-tree-vs-screenshot/): Compare accessibility trees, screenshots and structured perception for browser-agent workflows. - [AI Agents and RPA](https://e2llm.com/ai-agents-replace-rpa/): Compare AI agents and RPA by workflow stability, judgment, verification and governance. - [AI Browser Comparison](https://e2llm.com/ai-browser-comparison/): Compare AI browser approaches by perception, authenticated access, action precision and deployment. - [AI Form Filling](https://e2llm.com/ai-fill-online-forms/): Inspect, fill and verify online forms with human review before consequential submission. - [AI Agent Action Audits](https://e2llm.com/audit-ai-agent-actions/): Record intent, tool calls, observed state, action results and verification. - [Website Automation Without an API](https://e2llm.com/automate-website-without-api/): Automate rendered interfaces through grounded browser tools and verified state changes. - [Best Browser MCP Server](https://e2llm.com/best-browser-mcp-server/): Evaluate browser MCP servers by page understanding, session access, actions and verification. - [Browser Automation Without Screenshots](https://e2llm.com/browser-automation-without-screenshots/): Use structured page perception and explicit actions for text-first browser automation. - [Monitor Website Changes Behind Login](https://e2llm.com/monitor-website-changes-behind-login/): Compare authenticated page captures and alert on meaningful changes. - [n8n MCP Browser](https://e2llm.com/n8n-mcp-browser/): Connect an n8n AI Agent to browser tools through MCP. - [Ollama Browser Automation](https://e2llm.com/ollama-browser-automation/): Connect an Ollama-powered agent to browser automation through an MCP-capable host. - [Why Browser Agents Fail](https://e2llm.com/why-browser-agents-fail/): Recover from wrong targets, stale state and lost page context. E2LLM works in the user's real browser session, including authenticated pages. Enterprise deployments can run inside the customer's perimeter with the capture layer, MCP server, and model all inside the network. In E2LLM's benchmark, a structured read was roughly 5 to 15KB, compared with roughly 200 to 400KB for screenshot or raw-DOM approaches. ## Pricing - Free: $0, full product with a monthly usage cap. - Pro: $19/month, higher limits and longer sessions. - Pro+: $49/month, highest limits and longest runs. - Enterprise: custom, air-gapped deployment, customer model, and SSO. ## Trust and legal - [Security](https://e2llm.com/security/) - [Vulnerability Disclosure](https://e2llm.com/security/disclosure/) - [Incident History](https://e2llm.com/security/incidents/) - [Sub-processors](https://e2llm.com/security/subprocessors/) - [Privacy Policy](https://e2llm.com/privacy/) - [Terms of Service](https://e2llm.com/terms/) ## Company E2LLM is built by S2 Tikshuv Ltd as part of the Inlet ecosystem.