izscc

izscc / LongRun

Public

LongRun 将 GitHub Copilot CLI 打造为一个可调用的长时间运行任务的后端，供 Copilot、Codex、Claude Code 以及其他Coding Agents使用。

zscc.in
10
2
100% credibility
Found Apr 06, 2026 at 10 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A toolkit that enhances GitHub Copilot CLI to orchestrate long-running autonomous AI tasks for coding, research, and office automation with built-in planning, verification, recovery, and notifications.

How It Works

1
🔍 Discover LongRun

You hear about LongRun, a helpful add-on that lets your AI coding companion tackle big projects like coding marathons, deep research, or office reports without constant watching.

2
⚙️ Set it up quickly

Follow a simple one-click guide to add LongRun to your AI helper, including a full setup that prepares everything in your workspace.

3
🩺 Check everything's ready

Run a quick health check to confirm your AI is logged in and LongRun tools are working perfectly, with tips if needed.

4
🚀 Launch your first big task

Type a description like 'research electric car trends for 2025' and hit go – LongRun takes over, planning, working, and checking itself in the background.

5
📱 Peek at progress anytime

Use easy status checks or notifications to see how far along it is, and resume if you want to nudge it.

🎉 Enjoy perfect results

Get a cheerful alert when done, with organized files, summaries, sources, and proof everything checked out right – your project is complete and ready to use.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 10 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is LongRun?

LongRun transforms GitHub Copilot CLI into a lightweight backend for long-running tasks in coding, research, and office automation, letting you kick off autonomous sessions with commands like `longrun "task description"` or `/longrun` inside Copilot. Built in Python, it handles state tracking, artifact generation, and recovery across Copilot, Codex, or Claude Code agents via simple shell launchers. Developers get detached, resumable runs that maximize Copilot Pro quotas without babysitting sessions.

Why is it gaining traction?

It stands out with Opus-first model selection, automatic fallbacks, and macOS notifications for events like completion or blocks, keeping longruns at a steady pace without interrupting your flow. Cross-agent bridges mean one CLI entrypoint for multiple tools, plus verification gates that prevent premature closes. The hook? One-liner installs yield reliable, quota-efficient longruns, unlike brittle prompt chains or heavy platforms.

Who should use this?

CLI-heavy devs chaining Copilot for multi-step coding refactors, researchers scraping trends into reports, or ops folks automating office docs. Ideal for GitHub Copilot Pro users hitting rate limits on long sunday longruns, or agent tinkerers bridging Claude Code to Copilot's execution muscle.

Verdict

Try it if you're deep in Copilot CLI—solid for niche longrun herzfrequenz zoning, but at 10 stars and 1.0% credibility, it's early alpha with thin tests and Chinese-heavy docs. Polish the edges for production; uninstalls cleanly if it doesn't fit.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.