agent-hushInvisible privacy guardian for agent workspaces. Automatically intercepts outbound actions (git push, skill publish, file sharing) and checks for sensitive d...
Install via ClawdBot CLI:
clawdbot install elliotllliu/agent-hushGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badgeUses known external API (expected, informational)
raw.githubusercontent.comAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Developers frequently push code to public repositories like GitHub. Agent Hush automatically scans for exposed API keys or tokens in staged files before each git push, preventing accidental leaks of credentials such as GitHub tokens or AWS keys. This ensures secure collaboration without requiring manual checks.
When publishing AI agent skills to platforms like ClawHub, Agent Hush checks the entire skill directory for sensitive data like Slack tokens or database connection strings. It blocks publication if high-confidence secrets are found and offers to fix them, maintaining privacy in shared skill packages.
In collaborative workspaces, users often share files or code snippets with colleagues. Agent Hush intercepts file-sharing actions to scan for sensitive information such as private IPs or credit card numbers, providing a casual warning if low-confidence items are detected and letting the user decide.
Agent Hush runs background scans during routine heartbeats to detect new high-confidence secrets in the workspace, such as OpenAI keys or ID cards. It only interrupts the user for critical findings, enabling proactive privacy maintenance without disrupting workflow.
When users ask questions like '检查隐私' or 'scan for secrets', Agent Hush performs a full local scan and presents findings in a concise manner. It handles high-confidence leaks automatically and defers low-confidence items like emails or phone numbers to user discretion.
Offer a free basic version with automatic scanning for common secrets like GitHub tokens, and charge for advanced features such as custom allowlists, integration with CI/CD pipelines, and detailed analytics. Revenue comes from subscription tiers for teams and enterprises.
Sell licenses to large organizations for embedding Agent Hush into their internal development tools, with customization options for industry-specific compliance (e.g., healthcare or finance). Revenue is generated through annual contracts and support services.
Integrate Agent Hush into AI agent platforms or code repositories as a premium add-on, taking a commission on each transaction. For example, charge a fee for each skill published or code push scanned, leveraging existing user bases for scalable revenue.
💬 Integration Tip
Deploy Agent Hush by placing its scripts in the SKILL_DIR and configuring auto-triggers for outbound actions; use the .sanitize.json file to customize exclusions and allowlists for seamless workspace integration.
Scored Jun 19, 2026
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.
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
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...