DEDUPED Hot AI repos, turned into use cases Get the Monday 5

What you can do with Agentreach

AgentReach (reach) lets a coding agent running on your machine execute its shell commands and file operations on a remote box you can reach over SSH, without installing the agent or your API key on that box.

Trended earlier

bojieli/agentreach on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

5 use cases

  • Run Claude Code against a remote box without installing it there

    Point Claude Code at an SSH host so its shell and file work run on that host.

    View prompt
    Use the repo bojieli/agentreach to run Claude Code against <target>, for example build-box:/srv/app. Ask it what is using disk space on the target and confirm the commands ran there by checking `reach log`. Expected output: a disk usage summary from the target, and log entries showing exec commands with status ok.

  • Let Codex work on a client's server with no key left behind

    Run Codex against a remote project directory so its tools act on that server.

    View prompt
    Use the repo bojieli/agentreach to run Codex on <target>, for example client-box:/srv/app. Ask it to list the project files and report the current config value you name, then confirm the work ran remotely with `reach log`. Expected output: the file listing and config value from the server, plus log entries for the exec and write actions.

  • Run remote tests from a throwaway container or CI job

    Use a disposable container with reach to run commands on a target box.

    View prompt
    Use the repo bojieli/agentreach from its container image to run <command> on <target> through `reach <target> exec -- <command>`. Expected output: the command's stdout and an exit code. Verify that `reach <target> doctor` reports the target platform before the run.

  • Audit what an agent ran or changed on a server

    Use the reach log to review every command and write an agent made on a target.

    View prompt
    Use the repo bojieli/agentreach to review the actions taken on <target> during an agent session. Run `reach log` and report each exec and write entry with its status. Expected output: a table with WHEN, ACTION, STATUS and DETAIL columns that matches what the agent did.

  • Keep several remote machines open in parallel with one session each

    Open one reach session per box and track them with reach status.

    View prompt
    Use the repo bojieli/agentreach to list the active sessions on this machine with `reach status`, using <target> as a reference. Expected output: a table with NAME, TARGET, MODE, FILEOPS and CWD for each open session. Verify that a second command against the same target reuses its session.

How to use Agentreach

  1. Check you have what it needs: Go toolchain, or a pre-built reach binary from the releases page; An ssh binary on your machine that already reaches the target; The coding agent installed on your local machine, such as Claude Code or Codex.
  2. Open bojieli/agentreach on GitHub and read the README and license.
  3. Install reach with go install github.com/bojieli/agentreach/cmd/reach@latest
  4. Start the session with reach build-box claude, using your ssh_config alias or a host:path target
  5. Ask the agent a question about the box, for example what is using disk space, and let it run commands
  6. Review what it did with reach log

These steps come from our top use case, Run Claude Code against a remote box without installing it there, which also has a copy-paste agent prompt.

Agentreach alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and ops engineers who SSH into build boxes, staging servers, client machines or containers and want a coding agent to work there without installing it on the target.
  • Why it is hot
  • LanguageGo
  • Sourcegithub.com/bojieli/agentreach · Back to Hot repos

Requirements

  • Go toolchain, or a pre-built reach binary from the releases page
  • An ssh binary on your machine that already reaches the target
  • The coding agent installed on your local machine, such as Claude Code or Codex
  • Access to the target over SSH, with keys or config already set up

Add this badge to your README

Maintain Agentreach? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/bojieli/agentreach.svg)](https://dedupedai.com/use-cases/bojieli-agentreach/?utm_source=github&utm_medium=badge&utm_campaign=bojieli-agentreach)

HTML 

<a href="https://dedupedai.com/use-cases/bojieli-agentreach/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=bojieli-agentreach"><img src="https://dedupedai.com/badge/bojieli/agentreach.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Agentreach

What is Agentreach?

AgentReach (reach) lets a coding agent running on your machine execute its shell commands and file operations on a remote box you can reach over SSH, without installing the agent or your API key on that box. It is an open-source project on GitHub: https://github.com/bojieli/agentreach.

Who is Agentreach for?

Developers and ops engineers who SSH into build boxes, staging servers, client machines or containers and want a coding agent to work there without installing it on the target.

What can I do with Agentreach?

5 use cases so far, for example: Run Claude Code against a remote box without installing it there; Let Codex work on a client's server with no key left behind; Run remote tests from a throwaway container or CI job. Each has steps and a copy-paste agent prompt.

What do I need to run Agentreach?

Go toolchain, or a pre-built reach binary from the releases page; An ssh binary on your machine that already reaches the target; The coding agent installed on your local machine, such as Claude Code or Codex; Access to the target over SSH, with keys or config already set up.

What are alternatives to Agentreach?

Other hot AI repos in Software and DevOps: Omarchy Local AI, Hermes Plan Mode, Agent 2, Agnes Harness, Skills.

Is Agentreach safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.