agent-launch/agent-launcher

Configure and run existing coding-agent CLIs from one desktop app.

What it solves

Agent Launcher provides a unified desktop interface for managing and running various coding-agent command-line interfaces (CLIs). It eliminates the need to manually configure environment variables, manage multiple API keys across different agents, and switch between terminal windows for different AI coding tools.

How it works

The application acts as a local workspace that detects and links to existing agent CLIs installed on the system. It allows users to install missing agents via a one-click setup. Once linked, the app manages provider profiles (API keys and endpoints) and synchronizes these settings into the environment variables or native config files required by each specific CLI. It launches agents in an embedded terminal or chat view, using a project-aware session system that sets the working directory to the user's chosen project folder.

Who it’s for

Developers who use multiple AI coding agents (such as Claude Code, Codex CLI, and Gemini CLI) and want a single, organized dashboard to manage their configurations, sessions, and usage statistics.

Highlights

  • Unified CLI Management: Links to existing system installations of coding agents to avoid redundant installs.
  • Project-Aware Sessions: Remembers project folders and launches agents directly into the specific working directory.
  • Cofiguration Profiles: Supports multiple provider profiles per agent with connectivity checks to verify credentials before use.
  • Local-First Privacy: Stores API keys and session history locally; does not upload data to external analytics services.
  • Usage Dashboard: Summarizes token counts, request counts, and session data read from local CLI records.

Related

  • Project
    Jaysen13/jaysenwxapkg

    A Burp Suite extension for WeChat mini-program penetration testing that automates decryption, API extraction, and uses AI to infer request parameters from decompiled source code.

  • Project
    CyberSunil/LLMVault

    A deliberately vulnerable CTF-style training platform for learning the OWASP Top 10 for LLM Applications through scripted labs and real local model exploitation.

  • Project
    biusberline/cloudflare-turnstile-solver

    A Python library and CLI tool that automates the discovery of Cloudflare Turnstile sitekeys and generates valid tokens via the Peak API to bypass security challenges.

  • Project
    brycewang-stanford/StatsPAI

    A Python-native toolkit for applied causal inference and econometrics that replaces the need to switch between Stata and R for empirical research workflows.