|
Tachyonic - Sandboxes and security runtimes for AI agents
Run agent-written code in a sandbox. Test your agent endpoint with a bounded security runtime and review the evidence.
|
85 % |
|
mad-agentic.io | Agent Workspace
Agent Workspace / Control Center landing page for mad-agentic.io with runs, tools, memory, approvals, orchestration, and guardrails.
|
85 % |
|
TESTOS — AI Security Testing for LLM Apps, RAG, and Agents
Red-team LLM applications, RAG systems, and AI agents for prompt injection, jailbreaks, unsafe tool use, and data leakage before release.
|
85 % |
|
Runtime Guard - Any agent. Your rules.
Runtime Guard is an open-source MCP security layer for AI agent policy enforcement, runtime security, and destructive command protection. Runs local with no...
|
85 % |
|
Fuse AI | Block unsafe agent actions before execution
Fuse AI is a local-first runtime and diagnostic layer that checks AI agent tool actions before they hit APIs, files, databases, email systems, payment system...
|
85 % |
|
AgentSecOps — AI Agent Security Assessments & Hardening
AI-agent security readiness assessments for teams using coding agents, MCP servers, RAG bots, and autonomous workflows. Reduce the blast radius of prompt inj...
|
85 % |
|
Runwall — Execution Governance for AI Agents
Runwall is an agent-native execution governance platform. Policy enforcement, identity gateway, risk scoring, taint tracking, approval workflows, and audit t...
|
85 % |
|
General Analysis - AI Agent Security Platform
General Analysis secures AI agents from prompt injection, goal hijacking, and boundary breaches. Red-team testing and runtime guardrails for autonomous AI sy...
|
85 % |
|
MCP Gateway & AI Agent Authorization | Endram
Control AI agent and MCP tool calls with identity-aware policy, human approvals, one-use grants, and signed evidence.
|
84 % |
|
Oparento — Infrastructure for persistent AI agents
The runtime layer for persistent AI agents: execution, permissions, memory, identity, scheduling, sandboxing, and multi-agent coordination.
|
84 % |
|
EnvAI.io — Give AI agents a secure place to work
EnvAI.io provides autonomous AI agents with the context, tools, permissions, memory and isolated runtime required to complete real-world work.
|
84 % |
|
Veldt | Runtime Governance for AI Agents
Runtime governance for AI agents. Control what agents can do, detect attacks and abnormal behavior, contain compromise, prove every decision with verifiable...
|
84 % |
|
Herbert Runtime - AI-Native Runtime For The Web
Herbert Runtime is an AI-native execution layer designed for agents operating across web applications beyond public APIs.
|
84 % |
|
AgentWard — Secure every agent action, from install to runtime
Secure every agent action — from install to runtime. Source-available security platform for AI agents. Scan, enforce, detect, comply.
|
84 % |
|
Keely AI — Your AI Executive Team
AI agents that act as your C-suite, built for technical founders.
|
84 % |
|
Lelu - Authorization Engine for AI Agents
Authorization and security platform for AI agents. Control what your agents can do with confidence-aware gating, human oversight, and complete audit trails.
|
84 % |
|
Agent Legs — Give your AI agent the ability to act.
Agent Legs is the action execution layer for AI agents. Unified API for browsing, code execution, email, API calls, and file management — every action logged...
|
84 % |
|
AIDR | Agent Runtime Detection & Response
Runtime visibility, detection, investigation evidence, and phased response controls for enterprise AI agents.
|
84 % |
|
GeraGuard — Independent security control for AI agents
GeraGuard identifies AI agents, limits which data and systems they can access, stops dangerous actions before execution, and proves what happened. Built for...
|
84 % |
|
AgentOpsSec — Secure your agents before they touch your tools
AgentOpsSec is the open-source security and observability stack for AI agents. Local-first, MIT-licensed CLI tools that audit MCP servers, control tool calls...
|
84 % |
Detected social media networks