Item logo image for lfl-terminal

lfl-terminal

Item media 3 (screenshot) for lfl-terminal
Item media 1 (screenshot) for lfl-terminal
Item media 2 (screenshot) for lfl-terminal
Item media 3 (screenshot) for lfl-terminal
Item media 1 (screenshot) for lfl-terminal
Item media 1 (screenshot) for lfl-terminal
Item media 2 (screenshot) for lfl-terminal
Item media 3 (screenshot) for lfl-terminal

Overview

Browser terminal with deterministic commands and a local LLM that proposes page actions you approve. Nothing leaves your machine.

lfl-terminal is a keyboard-first terminal that lives in your browser. Press the backtick key on any page and a terminal overlay slides up. Type deterministic commands to read, search, navigate, and act on the page. For anything that needs interpretation, a local AI model (one you run yourself) proposes a single action that you approve or reject before it ever touches the page. The whole point is local-first, human-supervised control: - Nothing leaves your machine. Deterministic commands run entirely in your browser. The AI half talks only to a local model on your own computer (loopback, 127.0.0.1). There are no accounts, no servers, no telemetry. - The model proposes; you decide. Any action that changes the page (click, fill, navigate) is shown to you as a plain, deterministic summary and waits for your explicit approval. Read-only commands run without a gate. - The model is never a security boundary. Approval, the fixed set of allowed actions, and the hard blocks (for example, credential fields are never auto-filled) are enforced by the extension's own code, not by the model. What you can do: - Navigate and act: go, open, back, click, fill, search, scroll - Read and orient: read, ls, extract links/table, here - Find and highlight: find, highlight (mark every match on the page), matches (list them with context) - Make it yours: alias, macro, themes, per-site auto-open, a resizable and collapsible panel - Ask the local model: prefix a request with "ask" (or just type a plain request) and approve the single action it proposes Requirements (please read before installing): - You need a local, OpenAI-compatible model server running at http://127.0.0.1:1238 (for example llama.cpp's llama-server, LM Studio, or Ollama behind a compatible endpoint). The deterministic commands work without it; the AI proposals need it. - Chrome only, for now. What it will NOT do (on purpose): - It will not run shell commands, touch your filesystem, or use sudo. Ever. - It will not send your page content or commands to any cloud service or to us. - It will not act on a page without your approval for anything that mutates it. Open source (Apache-2.0). Source, threat model, and issues: https://github.com/MacadamiaButter/lfl-terminal

Details

  • Version
    0.4.0
  • Updated
    July 18, 2026
  • Offered by
    Macadamia Butter
  • Size
    122KiB
  • Languages
    English (United States)
  • Developer
    Email
    hello@localfirstlab.org
  • Non-trader
    This developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.

Privacy

Manage extensions and learn how they're being used in your organization
The developer has disclosed that it will not collect or use your data. To learn more, see the developer’s privacy policy.

This developer declares that your data is

  • Not being sold to third parties, outside of the approved use cases
  • Not being used or transferred for purposes that are unrelated to the item's core functionality
  • Not being used or transferred to determine creditworthiness or for lending purposes

Support

For help with questions, suggestions, or problems, visit the developer's support site

Related

PageGrok - Chat With Any Webpage Using Your Own AI

0.0

Ask your local AI about any webpage — no switching apps. Select text or parse the full page. Your data never leaves your computer.

AI Difference Engine

5.0

View page content like an AI crawler and analyze what’s available for LLMs.

AgentLimb

0.0

Let your terminal AI control your browser. Muscle memory cuts repeat-task tokens by 85%. 100% local — no cloud, no tracking.

我的 Bilibili 推荐

0.0

用 LLM 看你的 B 站行为生成兴趣画像,自动过滤推荐流

干活AI Web

0.0

Local browser bridge for AI reading and user-requested page actions in your own Chrome or Edge.

Ollama Client - Local AI Chat for Ollama, LM Studio, llama.cpp

4.6

Local-first private LLM chat with Ollama, LM Studio, and llama.cpp, with local RAG, web search, and page context.

WebShell — terminal, scraper & CSV for any webpage

0.0

A Unix-style terminal in any webpage: extract data to CSV, manipulate the DOM, and watch for changes with commands and pipes.

Autopilot Browser Automation

5.0

Automate your browser with AI. Autopilot sees your screen and walks you through software step-by-step. Real-time voice guidance.

HTML Text to .md — Local Markdown Web Clipper

5.0

Select any part of a page and convert it to clean Markdown. Tables, code and math stay intact. Runs locally in Chrome.

Browserfly - Your AI Agent in browser

3.3

Browserfly brings AI agents into your browser, helping you automate tasks smartly.

All Fingerprint Defender

3.9

Stable per-site fingerprint defense for Canvas, WebGL, Audio & fonts. Sites keep working, and nothing leaves your browser.

Definio AI: Multi-Modal AI Sidebar

4.9

Definio runs every LLM model from one sidebar. Throw your question at any of them, switch on a whim, never open a new tab.

PageGrok - Chat With Any Webpage Using Your Own AI

0.0

Ask your local AI about any webpage — no switching apps. Select text or parse the full page. Your data never leaves your computer.

AI Difference Engine

5.0

View page content like an AI crawler and analyze what’s available for LLMs.

AgentLimb

0.0

Let your terminal AI control your browser. Muscle memory cuts repeat-task tokens by 85%. 100% local — no cloud, no tracking.

我的 Bilibili 推荐

0.0

用 LLM 看你的 B 站行为生成兴趣画像,自动过滤推荐流

干活AI Web

0.0

Local browser bridge for AI reading and user-requested page actions in your own Chrome or Edge.

Ollama Client - Local AI Chat for Ollama, LM Studio, llama.cpp

4.6

Local-first private LLM chat with Ollama, LM Studio, and llama.cpp, with local RAG, web search, and page context.

WebShell — terminal, scraper & CSV for any webpage

0.0

A Unix-style terminal in any webpage: extract data to CSV, manipulate the DOM, and watch for changes with commands and pipes.

Autopilot Browser Automation

5.0

Automate your browser with AI. Autopilot sees your screen and walks you through software step-by-step. Real-time voice guidance.

Google apps