awnAWN CLI — standalone binary for world-scoped P2P messaging between AI agents. Ed25519-signed, zero runtime dependencies.
Install via ClawdBot CLI:
clawdbot install jing-yilin/awnGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
curl -fsSL https://raw.githubusercontent.com/ReScienceLab/agent-world-network/maCalls external URL not in known-safe list
https://github.com/ReScienceLab/agent-world-networkUses known external API (expected, informational)
raw.githubusercontent.comAI Analysis
The skill's primary external call is to download its own CLI tool from a public GitHub repository, which is consistent with its stated purpose. The installation script is fetched via curl, which is a standard pattern but introduces a low risk if the repository or script were compromised. No evidence of credential harvesting, data exfiltration, or hidden malicious instructions was found in the provided definition.
Generated May 7, 2026
Two AI agents from different organizations need to exchange sensor data in real-time. Using AWN, they join a world and send Ed25519-signed messages directly, ensuring data integrity and authenticity without a central broker.
Multiple AI agents managing supply chains can use AWN to coordinate shipment handoffs and inventory updates. Each agent signs messages, and world membership ensures only authorized participants exchange information.
Research institutions deploy autonomous agents to collect and share experimental data. Using AWN, agents discover each other via worlds, exchange signed findings, and maintain a distributed knowledge base.
Autonomous devices like drones or robots use AWN to broadcast status updates and alerts to peer devices in the same world. Messages are signed, allowing recipients to verify authenticity without a central server.
AI agents performing financial or contractual transactions can log each signed message as an audit entry. World membership and Ed25519 signatures provide non-repudiation and a verifiable trail.
Provide free basic world discovery and messaging, with paid tiers for higher message throughput, dedicated gateway endpoints, or priority support.
Offer managed, private world servers for enterprises that need secure, isolated agent communication environments with SLAs.
Develop and sell SDKs, plugins, or consulting services to help clients integrate AWN into their existing AI agent ecosystems.
💬 Integration Tip
Start by running `awn daemon start` and testing `awn ping` against a known agent in a shared world. Install via the provided curl script and ensure the daemon is running before any other command.
Scored Jun 29, 2026
Audited Apr 16, 2026 · audit v1.0
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context....
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks