AGGIB/Stroq

CLI tool

Get alerts like this View on GitHub Website Share on X

Can I trust it?

No red flags in our checks.

Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A local security tool for AI coding agents (Claude Code, Cursor, Codex CLI). It scans existing sessions for known secrets and reports which keys may have left the machine, and installs hooks that deny risky commands and ask before actions that repeat text the agent read. It has…

Who it's for

Developers using Claude Code, Cursor or Codex CLI who want to audit agent sessions and guard tool calls against secret leaks and prompt injection

How to use it

Install

npx @stroq/cli

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up AGGIB/Stroq in my project. Follow its README: https://github.com/AGGIB/Stroq. Explain each step and check it is safe before running anything.

Star curve

207From 15 to 207 stars between 2 Oct 2026 and 8 Nov 2026.

On the radar

Best place #89, on 6 Nov 2026. In the top 100 on 1 of the last 22 days.

Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.

Records

Best place on RepoAlerts: #89, on 6 Nov 2026
On the Hacker News front page on 5 Nov 2026

On Hacker News

Show HN: Stroq – a local audit of what your coding agent did and why92 points · 34 comments · 5 Nov 2026

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![AGGIB/Stroq on RepoAlerts](https://repoalerts.com/badge/AGGIB/Stroq.svg)](https://repoalerts.com/repo/AGGIB/Stroq?ref=badge)

Share on X

solongate/agent-security
Open-source Go security gateway for AI coding agents such as Claude Code and Codex. It checks tool calls against allow/deny policies before they run, detects and can redact or block secrets, applies r
AI agentsGo · 480 stars · 42 days old
Asymptote-Labs/agent-beacon
Open-source Go memory layer that captures coding agent session history across Claude Code, Cursor, Codex, OpenCode and other harnesses, and turns workflows, corrections and debugging patterns into rev
AppAI agentsGo · 3,369 stars · +393 this week · 180 days old
iamvicliu/AgentHub
Collects the local session histories of ten AI agents, including Claude Code, Codex and Cursor, into one list for unified search, reading and management. Sessions and the index stay on the local machi
AppApps & desktopTypeScript · 101 stars · +23 this week · 29 days old
DAgogo04/gogo-agent
A small, readable Python codebase for a local-first AI agent harness. It implements a plain loop (observe, reason, act), semantic, episodic and procedural memory stored in a local SQLite file, and a b
AgentAI agentsPython · 57 stars · 12 days old
collinzrj/claude-code-auto-safeguard-prompt
A system prompt and rule set for a security monitor that evaluates the latest action of autonomous AI coding agents and decides whether to block it. It defines hard and soft block categories covering
AI skillAI agents75 stars · +75 this week · 6 days old
mari8711/agent-runtime-kit
A typed, async Python runtime layer that runs coding-agent tasks through the Claude Agent SDK, OpenAI Codex SDK, or Google Antigravity SDK behind one shared task and result API. It reports unsupported
LibraryAI agentsHTML · 58 stars · 16 days old