Craft Anything is a desktop app and command-line tool that studies how a website, app or game works, then uses a coding agent to build your own version and check it against the original. It is meant for people who want to recreate or learn from existing software without writing it all by hand.
agent-autoloop
by KKKKhazix
Agent Autoloop is a lightweight automation hub that runs command-line AI agents such as Claude Code and Codex in the background on schedules or incoming events. It only contacts you, through desktop notifications or chat apps, when an agent needs a decision.
Proof level: ReadNew and promisingMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Needs a separate, already logged-in command-line agent, which may require a paid subscription or API usage.
Things to check
- Needs a separate, already logged-in command-line agent, which may require a paid subscription or API usage
- Agents run unattended and can consume tokens and change local code, so rules should be reviewed carefully
- Webhook channels (DingTalk, WeCom, Slack, Discord) and GitLab were only tested against local mock servers
- Documentation is primarily in Chinese, and the recipes were not tested on real accounts
- The install method pipes a remote script into the shell
Can you use agent-autoloop commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with agent-autoloop?
- Schedule a daily morning brief that summarises your notes and Git commits
- Have an agent pick up new GitHub issues and make local code changes, then ask you before anything risky
- Triage your unread email into a checklist with draft replies, or watch a website and get alerted when it fails
How do you get agent-autoloop running?
Install with a one-line PowerShell or curl script (needs Node 24 or newer, Git and an already logged-in command-line agent), then edit a rules.json file.
Follow the official instructions in the project README.
Make money with it
A freelancer could set up and maintain automated issue-handling, monitoring and reporting workflows for small clients as a paid service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Automate routine upkeep such as issue triage, website checks and inbox sorting, so a small team spends less time on repetitive work
- Handle customer feedback or alerts overnight, with the agent preparing fixes and replies and asking for approval only on sensitive actions
Who's talking about it
Checked 07 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in AI agents and automation
DSH Go is an unofficial Android app that runs the DeepSeek Harness coding agent on your phone, or lets you control a copy running on your computer or server. It gives you a chat interface for talking to AI models, approving tool actions and sharing conversations.
Orca is a desktop app, with a phone companion, for running several AI coding agents side by side, each in its own git worktree. It lets you track, review and steer their work from one place.