No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by slaveOftime · Codex Skill · ★ 94
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is open-relay safe to install? View the security audit →
oly — Open Relay https://github.com/user-attachments/assets/bd52a474-d9c4-48a7-824b-8df328a9d5a7 Run interactive CLIs and AI agents like managed services. gives long-running terminal jobs a durable home. Start a command once, detach, close your terminal, come back later, inspect logs, send input only when needed, or reattach and take over. It is built for AI agent workflows, interactive CLIs, and any session you do not want tied to one fragile terminal window. If saves you time, please star the repo. That helps more people discover it. For deep implementation details, see ARCHITECTURE.md, ARCHITECTUREPTY.md. Why people use Detach without losing the process. The daemon owns the session, not your terminal. Stop babysitting prompts. Watch logs or wait for likely input-needed checkpoints. Intervene surgically. Send text or keys without attaching. Resume with context. Reattach and replay buffered output first. Keep an audit trail. Session output and lifecycle events persist on disk. Control it from more than one place. Use the CLI, the web UI, or route work to connected nodes.
| Stars | 94 |
| Forks | 12 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 71.8533196470462/100 |
| Last Updated | 2026-09-20 |
| Created | 2026-03-08 |
| Platforms | claude-code, cli, codex, gemini, rust |
| Est. Tokens | ~24k |
These tools work well together with open-relay for enhanced workflows:
Looking for a open-relay alternative? If you're comparing open-relay with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Mobile companion for Claude Code, Gemini CLI & OpenCode. Encrypted, remote
Find that one coding agent session you want to get back to!
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
TUI / CLI config manager for agentic harnesses (Amp, Claude Code, Opencode, Goose, Copilot CLI, Crush, Droid)
One dashboard for all your local AI coding agents. Switch providers, manage sessions, and orchestrate tasks ac
Agent skills for Spec Kit
Explore other popular codex skill tools:
open-relay is oly turns long-running and interactive CLI workflows into persistent, supervised sessions for humans and AI agents. Close the terminal, keep the process alive, get notified when input is needed, and j. It is categorized as a Codex Skill with 94 GitHub stars.
open-relay is primarily written in Rust. It covers topics such as agentops, ai-agents, claude-code.
You can find installation instructions and usage details in the open-relay GitHub repository at github.com/slaveOftime/open-relay. The project has 94 stars and 12 forks, indicating an active community.
open-relay is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to open-relay on Agent Skills Hub include termly-cli, fast-resume, agnix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: