Browse Tools
Browse the definitive openclaw.ai tool directory. Every integration, plugin and agent — indexed, categorised and free to explore.
Filter by Category
ClawVault
ClawVault is a transparent proxy gateway that sits between your AI tools and the API, enforcing security policies, detecting sensitive data, blocking dangerous commands, and tracking token spend in real time.
ClawSecurity
ClawSecurity is an AI-powered security scanning platform for code, containers, and dependencies — built specifically for the agentic era.
ClawSecure
ClawSecure is an OpenClaw-specific security scanner that audits agent skills before installation and monitors them over time for code drift.
LobSec
LobSec is a security platform for the AI agent ecosystem — scanning skills and smart contracts for vulnerabilities, writing attestations on-chain (Base), and providing runtime protection for agent fle
SkillCheck by Repello AI
SkillCheck is Repello AI's public scanner for AI agent skills and MCP tools, designed to surface security vulnerabilities before deployment.
Clawsec
Clawsec is an open-source, YAML-configurable security middleware for OpenClaw agents that intercepts every tool invocation and runs it through a rules engine in under 5ms.
g0
g0 is an open-source security control layer for AI agent systems, built by Guard0.
ClawShell
ClawShell applies Linux-style permission models to AI agent secrets, treating agent execution as inherently adversarial compute that requires access control at the OS level.
DeClaw
DeClaw is a macOS-native local firewall for AI agents — a 100% local binary that sits between OpenClaw (or any AI app) and external AI providers, redacting PII before requests leave your machine and d
AgentKeys
AgentKeys is a credential proxy service that prevents AI agents from ever handling real API keys or OAuth tokens.
Crust
Crust is an open-source security gateway for AI agents, written in Go, focused on preventing agents from reading secrets or performing destructive/unauthorized actions.
HammerLock AI
HammerLock AI is a privacy-first desktop assistant that runs locally on your Mac with AES-256 encryption.
ClawBands
ClawBands is a security middleware layer for OpenClaw agents that intercepts tool calls before they execute and enforces human approval for anything deemed risky.
IronClaw
IronClaw is a secure, open-source OpenClaw alternative built in Rust that runs in Trusted Execution Environments (TEEs) on NEAR AI Cloud.
Keychains.dev
Keychains.dev is a credential delegation layer that lets AI agents call external APIs without ever seeing the underlying secrets.
xalgorix
xalgorix is an autonomous AI-powered penetration testing engine written in Go that runs comprehensive security assessments with minimal human intervention.
AgentGuard
AgentGuard is an open-source Python security framework for AI agents, built in direct response to the "Clinejection" attack that compromised 4,000 developer machines via a malicious GitHub issue.
PenClaw (Pingu Unchained by Audn.ai)
PenClaw points to Pingu Unchained, a 120B-parameter AI model from Audn.ai that is explicitly fine-tuned for offensive security red-teaming.
GuardClaw
GuardClaw is a deterministic runtime security layer for AI agents that blocks risky actions before they execute, without using an LLM to make those decisions.
SecurityClaw
SecurityClaw is an open-source autonomous SOC agent framework for teams running OpenSearch or Elasticsearch.
20 tools