Search

Portable OpenCode workflow toolkit — 6 plugins, managed agents & skills, a spec-to-code pipeline, security, and the vvoc CLI.

Zero-dependency epistemic security & PII guard for AI coding agents (Claude Code, Antigravity, Gemini CLI, Cursor)

CLI security scanner: probes AI-agent HTTP endpoints for secret/prompt leakage, with CI-gating exit codes.

🔐 Envlock — Secure credential vault for AI agents. Store, manage, and inject API keys without exposing them in chat.

Run any agent (Claude, Codex, custom) on any machine — with no API key on the machine. A secure, self-hosted proxy for models and tools.

Secure runtime for AI agents - isolated sandboxes with network isolation, PII scanning, prompt injection defense, and egress filtering.

Runtime security firewall for LLM agents — four-checkpoint scan engine, local-first with an optional hosted cloud tier

Multi-agent security monitoring SDK for LangChain / LangGraph — paired-event capture, real-time classification, and block mode.

Provider-agnostic QA testing for LLM-based agents: accuracy, robustness, fairness, and security checks with pass/fail reporting.

RantAI Agent is an AI powered cybersecurity agent that helps users execute real security tasks through intelligent automation and assistance.

Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.

CrewAI integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.

Security scanner for agent skill files - detects command injection, unsafe file operations, hardcoded secrets, and code injection risks

Security scanner for AI agent skills/plugins. Detects prompt injection, data exfiltration, excessive permissions, and supply chain attacks.

BSI/G7 SBOM-for-AI implementation — software, models, datasets, infrastructure, security, KPIs. With TIBET provenance + CBOM evidence linkage.

"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."

LangChain integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.

Security scanner for agent skill files - detects command injection, unsafe file operations, hardcoded secrets, and code injection risks

🔒 Correctover Agent Security Audit — test your AI agents for guardrail gaps in 5 seconds. Supports CrewAI, Smolagents, LlamaIndex.

Open-source autonomous AI assistant with 5-tier security, 62 tools, 14 LLM providers. Written in Rust. Single binary.