← Back to Skills Marketplace
Edge Router
by
adjusternwachukwu-bot
· GitHub ↗
· v1.0.0
· MIT-0
282
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install edge-router
Description
Route AI agent compute tasks to the cheapest viable backend. Supports local inference (Ollama), cloud GPU (Vast.ai), and quantum hardware (Wukong 72Q). Use w...
README (SKILL.md)
Edge Router
Routes tasks to cheapest available backend: local (free) → cloud GPU ($0.01) → quantum ($0.10).
API
Base: https://edge-router.gpupulse.dev/api/v1 (or localhost:3825)
Route (recommend)
curl -X POST "$BASE/route" -H "Content-Type: application/json" \
-d '{"task_type": "inference"}'
Execute (route + run)
curl -X POST "$BASE/execute" -H "Content-Type: application/json" \
-d '{"task_type": "inference", "payload": {"model": "llama3.2:1b", "prompt": "hello"}}'
Task Types
inference→ local first, cloud fallbacktraining→ cloud GPUquantum→ Wukong 72Qauto→ cheapest available
Other
GET /backends— list + statusGET /stats— routing statisticsGET /health— health check
Usage Guidance
This skill asks your agent to send task payloads to an external API (edge-router.gpupulse.dev) even though the skill metadata provides no source, homepage, or authentication details. Before installing: (1) do not send sensitive prompts/data through it; (2) ask the publisher for source code, a privacy/security policy, and API docs showing authentication and billing flow; (3) prefer a self-hosted or auditable router if you must route confidential workloads; (4) if you try it, run it in an isolated environment and monitor outbound network calls; (5) if you cannot verify the operator or code, treat this skill as a potential data-exfiltration risk.
Capability Analysis
Type: OpenClaw Skill
Name: edge-router
Version: 1.0.0
The skill instructs the agent to send task payloads, including potentially sensitive prompts, to an external third-party API (https://edge-router.gpupulse.dev/api/v1) as documented in SKILL.md. While the stated purpose is compute task routing across local, cloud, and quantum backends, the transmission of user data to an unverified external domain for 'execution' poses a significant data exposure risk. There is no evidence of intentional malice or backdoors, but the reliance on an external endpoint for processing arbitrary payloads is a high-risk behavior.
Capability Assessment
Purpose & Capability
Name and description match the SKILL.md: it routes tasks among local, cloud GPU, and quantum backends. However, the SKILL.md references specific providers (Ollama, Vast.ai, Wukong 72Q) but does not explain authentication, how it integrates with those providers, or why no credentials are required. It's plausible the router is a third-party aggregator, but the metadata gives no provenance or rationale for the lack of required credentials.
Instruction Scope
The runtime instructions tell the agent to POST task payloads (including model/prompt) to an external API endpoint (https://edge-router.gpupulse.dev/api/v1 or localhost:3825). That means arbitrary task data — potentially sensitive prompts, files, or inference inputs — would be transmitted off-agent to an unverified third party. There are no instructions about consent, redaction, or any limits on what may be sent. The agent is given direct network I/O instructions to a domain of unknown trustworthiness, which is scope creep relative to a simple local router helper.
Install Mechanism
No install spec and no code files (instruction-only). That minimizes on-disk risk. However, the lack of installer also means all action is via network calls to an external service defined in SKILL.md, which retains a high runtime trust requirement even though install risk is low.
Credentials
The skill declares no required environment variables or credentials. For a service that claims to route work to paid cloud/quantum backends, absence of any auth requirement is surprising. Either the aggregator handles billing (in which case you must trust it with all payloads and possibly account/billing info) or required credentials are missing from the spec. The lack of declared credentials increases the risk of unintended data exfiltration to an unauthenticated third party.
Persistence & Privilege
The skill is not marked 'always' and uses normal autonomous invocation defaults. It does not request to persist or modify other skills or system settings in the manifest. No privilege escalation signals in the provided metadata.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install edge-router - After installation, invoke the skill by name or use
/edge-router - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Smart compute routing: local → cloud → quantum
Metadata
Frequently Asked Questions
What is Edge Router?
Route AI agent compute tasks to the cheapest viable backend. Supports local inference (Ollama), cloud GPU (Vast.ai), and quantum hardware (Wukong 72Q). Use w... It is an AI Agent Skill for Claude Code / OpenClaw, with 282 downloads so far.
How do I install Edge Router?
Run "/install edge-router" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Edge Router free?
Yes, Edge Router is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Edge Router support?
Edge Router is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Edge Router?
It is built and maintained by adjusternwachukwu-bot (@adjusternwachukwu-bot); the current version is v1.0.0.
More Skills