Stroq

Stroq is a command-line tool that scans AI coding agent sessions for known credentials and guards future actions.

Stroq scans recorded Claude Code, Codex CLI, and Cursor sessions for values matching credentials stored on your machine. It identifies the specific credential and tool call without printing the secret value, helping secure your development environment. The tool reads local credential files to build a comparison index and checks historical records from before installation. It provides native hooks for Claude Code, Cursor, Codex, Copilot CLI, Windsurf, and Antigravity, alongside a plugin for OpenClaw and a stdio MCP proxy. Operating entirely locally with no outbound network calls from the hooks and no telemetry, Stroq is distributed under the Apache-2.0 license and requires Node.js 22 or newer.

Stroq at a glance

Best for: Software engineer
Runs on: CLI, self-hosted, open source
Pricing: Free
Released: September 2026
Category: AI coding tool
Website: github.com/aggib/stroq

Key features

Scans recorded Claude Code, Codex CLI and Cursor sessions
Matches known values in available tool arguments and results
Reports credential names and sources without printing values
Provides native hooks for multiple AI coding agents
Denies supported outbound calls containing a known secret
Operates locally with no outbound network calls or telemetry

Use it for

Scan historical AI coding sessions for exposed credentials
Guard future agent sessions against leaking known secrets
Trace risky commands using local hooks

Companions

Tools that articles about Stroq recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to Stroq

opcode — Turns terminal Claude Code workflows into an intuitive visual interface.
Claude Tap — Inspect prompts, tool calls, and token usage locally without a hosted dashboard.
Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
claude-mem — It shares persistent, searchable agent memory across sessions and devices.
pstack — Improves AI coding agent outcomes with rigorous workflows.
Coucou — It provides open-source, real-time agent monitoring and approvals directly from the screen notch.
Oracle — Provides a single entry point for multiple pro AI agents and session management.
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
Claude Scrub — Removes exposed API keys, passwords, and tokens from local AI session history.
Weir — It detects exact key values in agent logs and blocks them in coding sessions.
Claude Code Router — It centralizes control of AI agent requests with intelligent routing and observability.

All Stroq alternatives