
deadpush
a guardrail for vibe coding
Details
- Follow on
- @harris_ahmad55LinkedIn
- Categories
- AIDeveloper ToolsSecurity
- Target Audience
- AI DevelopersSoftware DevelopersBackend Developers
- Pricing
- Free
- Featured in
- Best ai security Tools
Discovery signals
How AI and people discover deadpush on PeerPush
About deadpush
Protects you from the mistakes, secrets, and context pollution that AI coding agents (Claude, Cursor, Windsurf, etc.) inevitably create — even when you're not watching. Run it once with deadpush protect --daemon and it runs in the background forever, monitoring your filesystem in real time. Key Features: - True background guardian — Survives terminal close, supports systemd/launchd autostart - Smart multi-agent Safety Score — Penalizes bursts of dangerous activity from parallel agents - Automatic quarantine (never hard-delete) — Easy deadpush quarantine list / restore - MCP proxy + Guardian Push Channel — Mandatory tool-path scanning and push incidents to agents - Plugin SDK — Extend enforce_content() via deadpush.guardrails entry points - Cross-platform git hooks — Pre-commit, post-commit, and pre-push guardrails - Debris detection — LLM context files, vibe scratchpads, hardcoded secrets One Command. Real Protection. pip install deadpush deadpush protect --daemon That's it. It will: - Install a smart pre-push git hook - Merge AI-specific ignore patterns into .cursorignore, .claudeignore, and .gitignore - Start a persistent background process that watches your entire repo - Automatically quarantine dangerous files the second they appear - Track a Safety Score that reacts intelligently when multiple agents are going wild
Reviews (0)
No reviews yet. Be the first to rate this product!
Comments (1)
deadpush exists because AI coding agents will write to files you never meant to touch. Filesystem quarantine, not code review — it locks down exactly what agents can touch. Built after a close call.