# Agent Autoloop 1.0 runs Claude Code and Codex in the background, asking only when you must decide

Canonical: https://theagenticweekly.com/news/agent-autoloop-1-0-background-cli-agents · Evidence: Reported · First seen: 2026-11-04 02:06 UTC · Source published: 2026-11-03 08:02 UTC · Brief published: 2026-11-04 03:04 UTC · Updated: 2026-11-04 03:04 UTC · Author: Agentic Weekly

> Agent Autoloop, an MIT-licensed open-source project, tagged v1.0.0 on GitHub on November 3, 2026. It runs command-line agents such as Claude Code and Codex in the background from schedules and events, and its README says "Any CLI tool that takes a prompt and prints a final reply can plug in."

## What changed

- The repository was created on November 3, 2026 and v1.0.0 ("Agent Autoloop 1.0.0") was tagged the same day; it installs with one curl command on macOS or Linux and needs Node 24, Git and a signed-in CLI agent.
- Rules in ~/.agent-autoloop/rules.json map a cron schedule, a GitHub webhook or an HTTP event to an agent and a working folder; built-in agent plugins cover Claude Code, Codex, ACP and any generic command.
- An agent works one round and exits; when it needs a decision it appends an agent-autoloop JSON block, and the hub sends a card to desktop notifications, Feishu, DingTalk, WeCom, Slack or Discord, then resumes the same conversation after you answer.
- Safety rules from the README: external text such as issue bodies never goes into the prompt, events carrying cwd, agent or access fields are rejected, and dispatch stops after 8 hops.
- The README reports a kernel of 1,651 lines with zero runtime dependencies, 88.78 ms cold start and 2,394 durable writes per second, measured on an Apple M5 Pro.
- A delivery plugin takes a GitHub PR labelled deliver through review, CI, merge, deploy and a live-version check, without checking out PR code on the worker machine.

## In the source's words

> "Any CLI tool that takes a prompt and prints a final reply can plug in."
> (Agent Autoloop README (GitHub), https://github.com/KKKKhazix/agent-autoloop/blob/main/README.en.md)

> "Past 8 hops, the kernel records the event, stops dispatching, and sends you a notice card."
> (Agent Autoloop README (GitHub), https://github.com/KKKKhazix/agent-autoloop/blob/main/README.en.md)

> "CLI output and default notification strings are currently in Chinese."
> (Agent Autoloop README (GitHub), https://github.com/KKKKhazix/agent-autoloop/blob/main/README.en.md)

## What we have not verified

- We did not install Agent Autoloop or run an agent through it.
- The benchmark numbers are the project's own, measured on one Apple M5 Pro machine; we did not reproduce them.
- The README says the DingTalk, WeCom, Slack and Discord templates were checked only against local mock servers, and the one-line commands for other agents (Cursor, pi, Hermes and others) have not all been run by the project.

## Timeline

- Source published: 2026-11-03 08:02 UTC
- First seen by our watcher: 2026-11-04 02:06 UTC (via GitHub new repos: topic mcp (discovery sweep); primary source is the GitHub repository)
- Brief published: 2026-11-04 03:04 UTC

## Sources

- [Agent Autoloop English README on GitHub](https://github.com/KKKKhazix/agent-autoloop/blob/main/README.en.md) (primary source) (fetched 2026-11-04)
- [Agent Autoloop v1.0.0 release](https://github.com/KKKKhazix/agent-autoloop/releases/tag/v1.0.0) (primary source) (fetched 2026-11-04)

## Related

- [Claude Code: verdict and setup guide](https://theagenticweekly.com/tools/claude-code)
- [Codex CLI: verdict and setup guide](https://theagenticweekly.com/tools/codex-cli)
- [All news briefs](https://theagenticweekly.com/news)
- [This week's releases](https://theagenticweekly.com/this-week)
- [New AI models this week](https://theagenticweekly.com/models/this-week)

## How to cite

Agentic Weekly, "Agent Autoloop 1.0 runs Claude Code and Codex in the background, asking only when you must decide", published 2026-11-04 03:04 UTC, https://theagenticweekly.com/news/agent-autoloop-1-0-background-cli-agents