RepoAlerts

pktq/lasik

CLI tool

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 7 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 6 days ago.

  • Licence OK

    MIT: 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 static CLI and MCP server that removes BLA (Blind LLM Agents) protection layers from builds, such as opaque predicates, encrypted strings, decoy code and prompt-injection text, and writes a cleaned copy. It never executes the input.

Who it's for

Developers and security analysts using coding agents or reverse-engineering tools on protected or obfuscated JavaScript, WebAssembly, Electron and binary builds

How to use it

Install

npm install -g lasik-agents

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 pktq/lasik in my project. Follow its README: https://github.com/pktq/lasik. Explain each step and check it is safe before running anything.

Star curve

133From 0 to 133 stars between 9 Nov 2026 and 16 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.

[![pktq/lasik on RepoAlerts](https://repoalerts.com/badge/pktq/lasik.svg)](https://repoalerts.com/repo/pktq/lasik?ref=badge)
Share on X

  • qybaihe/bla

    A defensive tool that hardens shipped software (binaries, Electron apps, JS bundles, Python, WebAssembly) against AI reverse-engineering agents. It plants decoys, exhausts analyzer resource budgets, a

    CLI toolAI agentsTypeScript · 5,915 stars · +1,624 this week · 23 days old

  • AGGIB/Stroq

    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

    CLI toolAI agentsTypeScript · 251 stars · +34 this week · 74 days old · HN 96 pts

  • ZiChuanLan/agent-purge

    A CLI and local web console that injects or replaces one shared system prompt (persona) across several coding agents such as codex, claude, opencode and pi. Changes are reversible and switchable at ru

    CLI toolAI agentsJavaScript · 1,867 stars · +368 this week · 23 days old

  • 0sec-labs/0security

    An open-source AI security harness with a local web interface for code analysis, pentesting, vulnerability research, reverse engineering, verification and fixing. It supports your own model provider a

    AppAI agentsTypeScript · 1,409 stars · +350 this week · 90 days old

  • yusuke-114/claude-xcode-agent

    A shell wrapper that runs Claude Code as the coding agent in Xcode 27 through the Agent Client Protocol. It loads API keys, gateway URL, model and MCP servers from a config.json file and skips the glo

    AI skillAI agentsShell · 81 stars · +81 this week · 8 days old

  • muaaz9329/cheap-ag

    An MCP server for Claude Code that delegates code writing to a low-cost model through OpenRouter, DeepSeek, OpenCode Go or Command Code, while Opus plans. Each change must pass tests run by Cheap Agen

    MCP serverAI agentsTypeScript · 333 stars · +19 this week · 19 days old