Radar / Categories / AI security
New AI security, ranked by traction
New AI identity, compliance and security tooling. Every launch from the last few weeks, ranked by JEV traction and GitHub stars. Updated four times a day.
Compliance · 22
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68NVIDIA OpenShell joins CNCF: open governance for securing autonomous agentsNVIDIA contributed OpenShell, its open-source runtime for securing and governing autonomous agents, to the CNCF as a…security · JEV 0.68sapper-v2: autonomous pentest legion with an AI commander and worker swarmsapper-v2 is an autonomous penetration-testing system: an AI commander directs a worker swarm over a layered…security · JEV 0.6Claude-Cage: a lightweight VM that stops Claude leaking to the networkA lightweight virtual machine built for Claude that blocks network leaks, with multi-platform support, multi-account…security · JEV 0.59BLA: adversarial defense shield that poisons, exhausts and hallucinates AI reverse-engineering agentsTypeScript shield protecting binaries, Electron apps, JS bundles, Python and WebAssembly against AI…security · JEV 0.47Anthropic sandbox-runtime: OS-level sandboxing for AI agents, no containers requiredAnthropic's sandbox-runtime (srt) is trending with developers this week: an open-source tool that wraps any process in…security · JEV 0.45VoidAccess: open-source, self-hosted dark web OSINT platformSelf-hosted dark-web OSINT platform (892 stars) that takes automated threat intelligence from query to a graph…security · JEV 0.42PlugVetAn independent public directory that grades AI agent skills, plugins, and MCP servers with evidence-backed hygiene…security · JEV 0.42Cisco Project Quarry: open-source behavior detection engine for AI agentsCisco open-sourced Project Quarry on 28 Oct 2026: a behavior detection engine that watches AI agents at the session…security · JEV 0.42CrowdStrike Agentic Adversary Emulation: AI red teams that chain attack pathsUnveiled November 4 at Fal.Con Europe, Agentic Adversary Emulation on the Falcon platform uses SafeMind's Red Tempest…security · JEV 0.38Detectify Agentic Tooling: prove what your AI security agent actually testedDetectify's new tooling lets an organization's own AI agents investigate suspected vulnerabilities against live…security · JEV 0.3OpenAI Patch the Planet: coordinated disclosure program for AI-discovered vulnerabilitiesOpenAI launched Patch the Planet, an initiative with Trail of Bits that coordinates security researchers, open-source…security · JEV 0.29Arcjet AI security models: custom prompt-injection detectors for coding agentsArcjet ships a family of compact, custom-trained security models that catch prompt injection in AI agent activity.security · JEV 0.29kosa8: air-gapped microVM sandboxes for enterprise AI agentskosa8 gives every AI agent its own sealed microVM with its own kernel, a closed-by-default network, API keys kept on…security · JEV 0.25BotGauge: red-team platform that attacks AI agents, traces failures and turns each break into a permanent evalAgent red-teaming platform with 200+ attack strategies, full execution tracing, and evals that rerun on every release.security · JEV 0.18Privacyboard: privacy compliance on autopilotPrivacyboard detects the tools a company uses and drafts its privacy policy, cookie banner, records, and DPA in…security · JEV 0.17Antelog: stop AI coding agents from leaking or destroying your dataStops AI coding agents from deleting databases, wiping files, or leaking secrets — before it happens.security · JEV 0.17
Identity · 7
Anthropic FlashProve: cryptographic proof of which AI model actually answeredAnthropic open-sourced FlashProve, a research prototype that uses zkSNARKs to prove a response came from one specific…security · JEV 0.53Agentic Identity Broker: OAuth delegation for AI agentsMIT-licensed OAuth2 broker from the Zalando Incubator that lets a user give an AI agent scoped, revocable access to…security · JEV 0.431Password for Agents: personal AI agents sign in without ever seeing the password1Password launched 1Password for Agents on Oct 22, 2026: when a supported personal agent hits a sign-in page, it…security · JEV 0.39Alter (YC S25): zero-trust identity and access control for AI agentsAlter (YC S25) launched a zero-trust identity and access-control platform for AI agents, sitting in the middle of…security · JEV 0.31OpenMail: an email identity for every AI agentOpenMail gives each AI agent its own inbox on a team's own domain, with inbound mail delivered over webhook or…security · JEV 0.23Puffin: identity and inboxes for AI agentsIdentity and inboxes for AI agents: a real email address, calendar, and chat seats per agent.security · JEV 0.2Veqen: AI spend ledger that catches a leaked API key by its spend, usually within the hourCross-provider AI cost monitoring that attributes every charge to a person, customer or project, flags spend nobody…security · JEV 0.19
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.