dreamerron

dreamerron/SafeBrowse-Agent

A consent-first real AI browser agent with hard-coded safety rails. Automates navigation, clicks, and forms under 15 non-negotiable rules: no touching sensitive data, no script injection, no deception, no CAPTCHA/ToS bypassing. Sandboxed, rate-limited, fully logged — every action announced, high-risk steps require your explicit approval.

4 good first / help-wanted issues · TypeScript · last activity Sep 2, 2026

0 stars 0 forks 0 watchers TypeScript MIT License
4 Open Issues Need Help Last updated: Sep 2, 2026

Open Issues Need Help

View All on GitHub
dreamerron/SafeBrowse-Agent
0

A consent-first real AI browser agent with hard-coded safety rails. Automates navigation, clicks, and forms under 15 non-negotiable rules: no touching sensitive data, no script injection, no deception, no CAPTCHA/ToS bypassing. Sandboxed, rate-limited, fully logged — every action announced, high-risk steps require your explicit approval.

TypeScript
good first issue vocab
dreamerron/SafeBrowse-Agent
0

A consent-first real AI browser agent with hard-coded safety rails. Automates navigation, clicks, and forms under 15 non-negotiable rules: no touching sensitive data, no script injection, no deception, no CAPTCHA/ToS bypassing. Sandboxed, rate-limited, fully logged — every action announced, high-risk steps require your explicit approval.

TypeScript
good first issue vocab
dreamerron/SafeBrowse-Agent
0

A consent-first real AI browser agent with hard-coded safety rails. Automates navigation, clicks, and forms under 15 non-negotiable rules: no touching sensitive data, no script injection, no deception, no CAPTCHA/ToS bypassing. Sandboxed, rate-limited, fully logged — every action announced, high-risk steps require your explicit approval.

TypeScript
good first issue vocab
dreamerron/SafeBrowse-Agent
0

A consent-first real AI browser agent with hard-coded safety rails. Automates navigation, clicks, and forms under 15 non-negotiable rules: no touching sensitive data, no script injection, no deception, no CAPTCHA/ToS bypassing. Sandboxed, rate-limited, fully logged — every action announced, high-risk steps require your explicit approval.

TypeScript