Support

Clone the repository from GitHub, open Chrome and go to chrome://extensions, enable Developer Mode, click "Load unpacked" and select the FSB folder. The extension icon will appear in your toolbar.

We recommend xAI Grok 4.1 Fast for the best balance of speed and accuracy. It has a 2M token context window and costs $0.20/$0.50 per million tokens. For a free hosted option, try Gemini 2.0 Flash (experimental). For maximum quality, use Claude Opus 4.1 or Grok 4.1. If you want broad model access, use OpenRouter. If you want a privacy-friendly local setup with no API key, use LM Studio.

FSB supports Chrome 88+ and all Chromium-based browsers including Microsoft Edge, Brave, Opera, and Vivaldi. Firefox support is planned for a future release.

Yes. API keys are encrypted using AES-GCM before being stored in Chrome's local storage. They are only decrypted in-memory when making API calls. Keys are never logged, exported, or transmitted to any server other than your chosen AI provider.

FSB includes action validation and safety checks. It only performs actions on the current tab and only when explicitly instructed. All code is open source and auditable. That said, use caution with tasks involving sensitive accounts or financial transactions -- always review what FSB is doing.

Open an issue on the GitHub Issues page. Include the website URL, your task description, and any error messages from the FSB chat or browser console. Session logs from the Debug tab in Options can also help.

MCP (Model Context Protocol) lets you control FSB from AI coding tools like Claude Code, Codex, Cursor, Windsurf, and OpenClaw. The MCP server runs as npx -y fsb-mcp-server and pairs with the running extension over a local WebSocket bridge -- FSB exposes 50+ browser actions as MCP tools (click, type, navigate, read DOM, fill vault credentials, and more). For OpenClaw users specifically, the fastest path is the one-click install on ClawHub at clawhub.ai/lakshmanturlapati/full-selfbrowsing, or load the FSB skill at skills/FSB Skill/ which prints the stdio config block and runs the doctor diagnostic. The full rundown lives at the Agents page.

Connect FSB as an MCP server, then let the coding agent open the local app, click through real flows, observe DOM state, capture console or task errors, and report failures back into the coding session. This closes the manual loop between code generation, browser testing, logging, and fixing.

Yes. The Remote Dashboard at full-selfbrowsing.com lets you pair with your FSB extension via QR code, then send tasks, view a live DOM preview of the browser, and monitor current execution state from any device with a web browser.

FSB has a local memory system with three layers: semantic memory (site navigation patterns), episodic memory (past action sequences), and procedural memory (successful workflows). This data stays on your device and helps FSB navigate familiar sites faster and avoid repeating mistakes. Memory auto-consolidates after enough sessions.

Run npx -y fsb-mcp-server install --list to see which MCP hosts the installer detects on your machine, then run the installer for one (for example npx -y fsb-mcp-server install --claude-desktop). Cursor, Codex, Windsurf, and others have matching flags from --list. For OpenClaw, paste the canonical stdio block printed by the FSB skill (loaded from skills/FSB Skill/) into your OpenClaw MCP config -- the bare --openclaw installer flag is intentionally manual because OpenClaw's MCP config schema is still unstable across builds. Verify the install with npx -y fsb-mcp-server doctor; six green layers means you're ready.

FSB exposes two modes through MCP. Manual mode is the default and gives the calling agent 50+ granular tools -- navigate, click, type, scroll, read page state, take screenshots, fill spreadsheets, fill vault credentials, and more. Autopilot mode (run_task) only fires when the user explicitly delegates the whole task -- phrases like "use FSB autopilot", "delegate this", or naming run_task directly. For everything else the calling agent stays in the loop on every action, which is exactly what coding agents want when they're testing an app in-browser and feeding observations back into the editor.

Three options, fastest first. One-click on ClawHub: install from clawhub.ai/lakshmanturlapati/full-selfbrowsing. FSB skill: load the skill from skills/FSB Skill/ in the FSB repo -- it prints the canonical OpenClaw stdio block for you to paste into OpenClaw's MCP config and offers consent-gated install for any other MCP hosts on your machine. The full 3-step walkthrough (Chrome extension, MCP server config, doctor verification) lives at the Agents page.

Run npx -y fsb-mcp-server doctor. The doctor walks six layers -- package, bridge, extension, active-tab, content-script, config -- and exits non-zero on the first failure with a one-line next-step recommendation. The full recovery table for each layer lives in skills/FSB Skill/USAGE.md, and the same diagnostic runs automatically when the FSB skill is loaded into OpenClaw.