Maintainer of this skill?
Automated security scan — not a certification.
by slaveOftime
oly runs coding agents and long-running commands in persistent, supervised terminal sessions. The daemon owns the PTY, so you can close your terminal and come back from the browser or your phone.
# Add to your Claude Code skills
git clone https://github.com/slaveOftime/open-relayLast scanned: 10/22/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-10-22T09:11:31.717Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how open-relay compares with popular alternatives.
open-relay is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by slaveOftime. oly runs coding agents and long-running commands in persistent, supervised terminal sessions. The daemon owns the PTY, so you can close your terminal and come back from the browser or your phone. It has 103 GitHub stars.
Yes. open-relay passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/slaveOftime/open-relay" and add it to your Claude Code skills directory (see the Installation section above).
open-relay is primarily written in Rust. It is open-source under slaveOftime on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh open-relay against similar tools.
No comments yet. Be the first to share your thoughts!
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Run an interactive CLI once. Close your terminal. Come back from another terminal or a browser — with the process still running and its output recorded.
oly is a local-first session supervisor for coding agents, REPLs, and
long-running commands that still need a human in the loop. It runs the CLI you
already use — no model-provider integration — and serves both the oly ls --follow dashboard and a password-protected web UI at http://127.0.0.1:15443.
Think persistent terminal sessions + a supervision API, not another agent framework. Use your shell for quick commands; use oly when a job needs a durable home.
Terminal dashboard — oly ls --follow --node-all --limit 5000 lists every session, or groups them by working directory.
| List view | Tree view |
|---|---|
 |
 |
Browser UI — the same daemon from any device, with live status and one-click attach.
On a phone — the web UI installs as a PWA, so you can check a prompt and answer it without a laptop.
| Sessions | Detail |
|---|---|
 |
 |
npm install -g @slaveoftime/oly
The npm package bundles binaries for Linux x64, Linux arm64, macOS Apple Silicon, and Windows x64. No GitHub asset download is needed during installation.
0.5.0-beta.3 is available: a breaking preview, not the stable channel. Stable installs still use the 0.3 line. Try
npm install -g @slaveoftime/oly@betaor the GitHub prerelease. Back up state and read the migration guide before upgrading. See the release notes and verification.
Homebrew (stable):
brew tap slaveOftime/open-relay https://github.com/slaveOftime/open-relay
brew install slaveOftime/open-relay/oly
Prebuilt binaries: download a platform archive from GitHub Releases.
Cargo (stable):
cargo install oly
Building from source requires Rust and Node.js/npm: release builds compile and embed the web UI. See Contributing for development setup.
# Start the daemon (skip this if it is already running).
# Default: password-protected web UI at http://127.0.0.1:15443.
oly daemon start --detach
# Run your preferred CLI in the background; save the returned session ID.
oly start --detach copilot
# See sessions and inspect recent output.
oly ls
oly logs <id> --tail 40
# Inspect a TUI and, after reviewing its prompt, reply without attaching.
oly logs <id> --screen
oly send <id> "continue" key:enter
# Take over interactively. Ctrl-D detaches; the child keeps running.
oly attach <id>
Replace copilot with claude, codex, another agent, or any interactive
command. Pass oly options before the child command.
Open http://127.0.0.1:15443 for the browser UI, or use
oly ls --follow --node-all --limit 5000 for the live terminal dashboard.
| Want to… | Command |
|---|---|
| Wait for a likely checkpoint | oly logs <id> --wait prompt --timeout 5m |
| Inspect metadata and exit status | oly info <id> / oly info <id> --json |
| Watch without sending input or resizing | oly attach <id> --observe |
| Interrupt the child | oly send <id> key:ctrl+c |
| Export recorded display bytes | oly export <id> > capture.bin |
| Stop a session | oly stop <id> |
| Start a fresh run from saved launch metadata | oly restart <id> |
| Teach an agent how to supervise sessions | oly skill / oly skill --subagent |
restart launches a new run.oly node peer management, and notificationsMIT licensed. If oly makes your workflow easier, a star on GitHub helps others find it.