Stroq
Scans what the agent reads, taints the session, blocks the dangerous follow-up — before anything leaves your machine. Open source, Apache-2.0.
Overview
Stroq scans what your AI coding agent reads, taints the session, and deterministically blocks the dangerous follow-up action — locally, with a hash-chained audit log. Open source, Apache-2.0. One command to install into Claude Code, Cursor, Codex, Copilot CLI, Windsurf, OpenClaw or any MCP client.
Stroq appears to provide a local action firewall for AI coding agents, scanning and tainting sessions to block potentially dangerous follow-up actions based on what the agent reads. It emphasizes a zero-config installation and operates without sending data to the cloud.
Sources behind this listingSee source links, recorded dates and owner corrections.
Observed facts come from public pages. Founder-edited facts are supplied by the verified owner. AI-inferred facts are model interpretations; derived facts are calculated from other data. A source link lets you check the current page. It does not guarantee the fact is still current.
Dates show when a record was saved. Some older records use the listing’s update date; they are not proof of a fresh check. Missing source records are shown explicitly.
- TaglineScans what the agent reads, taints the session, blocks the dangerous follow-up — before anything leaves your machine. Open source, Apache-2.0.
- Source not recordedDate not recordedSource link unavailable
- DescriptionStroq scans what your AI coding agent reads, taints the session, and deterministically blocks the dangerous follow-up action — locally, with a hash-chained audit log. Open sourc...
- Source not recordedDate not recordedSource link unavailable
- Free planYes
- Source not recordedDate not recordedSource link unavailable
- Free trialNot stated
- Source not recordedDate not recordedSource link unavailable
- IntegrationsGitHub
- Source not recordedDate not recordedSource link unavailable
- SummaryStroq appears to provide a local action firewall for AI coding agents, scanning and tainting sessions to block potentially dangerous follow-up actions based on what the agent re...
- AI-inferredRecorded Source link unavailable
Who Is It For
Developers seeking to enhance the security of their AI coding agents by preventing harmful actions based on untrusted content.
Organizations that require extensive cloud integration or those looking for a fully managed security solution.
Strengths & Weaknesses
The tool's ability to operate locally without relying on external networks or cloud services, ensuring that all actions are processed on the user's machine.
Alternatives to Stroq
Community
No comments yet. Be the first to share your experience.