Show HN: Relay – OpenClaw용 오픈 소스 Claude Cowork

What Is Relay · Why Relay · Features · Use Cases · Quickstart · Development If OpenClaw is the runtime, Relay is your local command center. Relay is an Electron desktop app that gives you the same workflow as Claude Cowork (autonomous task execution, scheduling, sub-agents, connectors) but running on your infrastructure, with your choice of model, and with real governance built in. Cowork is a great product. But there are three structural limits that push companies toward alternatives: - Data sovereignty. Cowork processes your files on Anthropic's infrastructure. If you're in a regulated industry or have strict data policies, that's a dealbreaker. - Model lock-in. Cowork only works with Claude. If you want to route tasks to GPT-4, Llama, Gemini, or a custom endpoint, you're out of luck. - Compliance gaps. Anthropic themselves recommend against using Cowork for regulated workflows because activities aren't yet captured in standard audit logs or compliance APIs. Relay solves all three. Same workflow pattern, different trust model. ┌──────────────────────────────────────────────────────────────────────────┐ │ You (Operator) │ │ give goals · review deliverables · approve risky actions │ └─────────────────────────────┬────────────────────────────────────────────┘ │ ┌───────────────▼────────────────┐ │ Relay (Desktop App) │ │ ── Control Plane ── │ │ │ │ Dispatch & Chat │ You see everything. │ • Give a task in natural lang │ You approve what matters. │ • Agent plans steps for you │ You stay in control. │ • Review polished deliverable │ │ │ │ Governance │ │ • Approval gates (file ops, │ │ shell commands, data sends) │ │ • Exportable audit trail │ │ • Cost tracking per task │ │ │ │ Configure │ │ • Schedule recurring tasks │─ ─ ┐ Relay defines. │ • Browse & edit agent memory │ │ OpenClaw executes. │ • Manage connectors (Slack, │ │ │ Notion, GitHub, Jira, etc.) │ │ │ • Set project working folder │ │ └───────────────┬────────────────┘ │ │ │ WebSocket / API │ │ │ ┌───────────────▼────────────────┐ │ │ OpenClaw Gateway (Runtime) │◄ ─ ┘ │ local · VPS · custom URL │ │ ── Execution Plane ── │ │ │ │ Agent Runtime │ Runs on YOUR infra. │ • Autonomous task execution │ Your keys. Your data. │ • Multi-step planning & tools │ │ • Sub-agent orchestration │ │ │ │ Persistence │ │ • Memory storage & retrieval │ │ • Schedule runner (cron) │ │ • File read / write / search │ │ │ │ Integrations │ │ • Connectors (Slack, Notion, │ │ GitHub, Jira, email, etc.) │ │ • Computer use (browser, UI) │ │ • Shell / script execution │ │ │ │ Model Router │ │ • Routes to any LLM backend │ └──┬──────────┬──────────┬───────┘ │ │ │ ┌─────▼───┐ ┌────▼───┐ ┌────▼─────┐ │ Claude │ │ GPT-4 │ │ Llama │ │ Gemini │ │ Mixtral│ │ Custom │ └─────────┘ └────────┘ └──────────┘ Relay is the control plane — you see, configure, and approve. OpenClaw is the execution plane — agents run, remember, and act on your infrastructure. Example: Scheduled daily briefing Relay (you define) OpenClaw (it executes) ────────────────── ────────────────────── Create schedule: "Daily 8am" ──────► Stores schedule Set connectors: Slack + Notion Cron fires at 8am Agent reads project files Pulls Slack threads & Notion pages Calls LLM (your model choice) Writes briefing to memory Briefing appears in Relay ◄────── Returns deliverable You review, approve, or redirect Full audit trail exported OpenClaw is multi-agent by design. Relay treats this as an operator-visible runtime model: - Agent = the runtime identity that owns a task (role, memory scope, policy profile, model routing). - Skill = the capability bundle an agent can use (tools, instructions, schema expectations, policy requirements). - Node = the execution environment where work runs (local Docker, SSH host, managed runtime) with concrete limits and health. Run contract: - Each run is assigned to one primary agent. - The agent executes using one or more skills. - The run executes on a selected node. - Any consequential action should remain attributable to agent + skill + node in the audit trail. Relay role in this model: - Select and display which agent is active. - Show which skills are available and why an action is or is not possible. - Surface node selection, node health, and node-level limits. - Keep approvals and activity logs tied to runtime identity, not only chat text. Canonical definition: docs/RELAY-OPENCLAW-AGENT-SKILL-NODE-MODEL.md | Problem | How Relay handles it | |---|---| | Data sovereignty | Your files stay on your machine. Agents run on your server. Your keys. | | Model lock-in | Use any LLM through OpenClaw: Claude, GPT-4, Llama, custom endpoints. | | No compliance-ready audit | Full audit trail with exportable execution history, approval records, and action rationale. | | Always-on execution | Agents run 24/7 on a VPS while you control them from the desktop. | | Token cost at scale | Cowork burns through plan limits fast. With Relay + OpenClaw you manage costs on your own infrastructure. | | Syncing friction | Your