|
AgentAuth - Passport for AI Agents | Soul Layer, ZKP, Anti-Drift
AI Agent authentication with Soul Layer persona system, zero-knowledge proof verification, and anti-drift behavioral monitoring. Open source, developer-first.
|
88 % |
|
AgentCodeFactory - Multi-Agent AI Code Generation Platform
Enterprise-grade code generation with specialized AI agents. Multi-agent pipeline, RAG enhancement, policy enforcement, GitHub automation. Use any LLM - Open...
|
87 % |
|
AgentCop — AI Agent Security Scanner
Free AI agent security scanner. Real AST taint analysis, OWASP LLM Top 10 coverage, CWE-mapped findings. Scan LangGraph, CrewAI, AutoGen, OpenClaw agents. No...
|
87 % |
|
AI Agent Security & MCP Authorization Gateway — AgentGate Labs
AgentGate checks every AI agent MCP tool call before it runs: default-deny policy, request-bound human approvals, gateway-held credentials and exportable aud...
|
87 % |
|
Effortlessly add auth and permissions to your MCP servers and AI Agents!
Empower your AI engineers to ship securely MCP servers and AI agents from prototype to production.
|
86 % |
|
AI agent asset security | Optimus Labs
Optimus Labs secures the AI agent supply chain: the SKILLs, MCP servers, plugins, and agent harnesses your employees run. Map what each can reach, inspect fo...
|
86 % |
|
OWASP FinBot CTF - The Juice Shop for Agentic AI
OWASP FinBot is an Agentic Security CTF platform by the OWASP GenAI Security Project. Hack AI agents, exploit prompt injection, and learn to secure agentic s...
|
86 % |
|
Truvant — Policy Enforcement for AI Agent Actions
Control what your AI agents can do. Scan, enforce policy, and monitor every MCP server, skill, and plugin — before, during, and after every action.
|
86 % |
|
Truvant — Policy Enforcement for AI Agent Actions
Control what your AI agents can do. Scan, enforce policy, and monitor every MCP server, skill, and plugin — before, during, and after every action.
|
86 % |
|
AgentShield
Test your AI agent against 57 adversarial scenarios. Trace every call. Enforce budgets. Catch policy violations. Set up in 9 lines of code.
|
86 % |
|
AgentGuardX — AI Agent Security Toolkit
AgentGuardX is an open-source red-teaming toolkit for testing the security of LLM-powered agents. Audits prompt injection, memory poisoning, and tool abuse o...
|
86 % |
|
Sunglasses | The Input Firewall for AI Agents | Open Source AI Agent Security
Sunglasses is an open source filter that blocks prompt injection and MCP tool poisoning before it reaches your AI agent. Local first, MIT licensed.
|
85 % |
|
ActPass: stop risky AI agent actions before they execute
ActPass sits between your AI agents and their tools: every risky action gets a deterministic, signed allow/deny decision and a tamper-evident audit trail.
|
85 % |
|
AI Agent Security & Control Platform | Oso for Agents
Oso helps companies run agents in production with confidence using monitoring, access controls, and automated least privilege.
|
85 % |
|
Oktsec | AI Agent Security & Governance
AI agent security and governance: pentesting, dependency review and runtime controls. Assess a system, plan an AI pilot or train your team with Oktsec.
|
85 % |
|
Approve AI - User Approval for AI Agents
Add user approval workflows to your AI agents with a simple integration.
|
85 % |
|
fischer³ — Open Source Security Software with Mathematical Foundations for the Agentic AI Era — fischer³
fischer³ builds open source security software for the agentic AI era. Home of Zero Trust AI, Agent Scrutiny, and the Agentic Security Education project.
|
85 % |
|
Approve AI - User Approval for AI Agents
Add user approval workflows to your AI agents with a simple integration.
|
85 % |
|
HackAgent - Security for AI Agents
The package to test against injection and jailbreaking. Build AI Agents You Can Trust.
|
85 % |
|
AgentShield — Open-Source Prompt Injection Detection for AI Agents
Open-source security middleware for AI agents and RAG pipelines. Detect prompt injection attacks using ZEDD, monitor embedding drift, and gain threat intelli...
|
85 % |
Detected social media networks