Skip to main content

Solo.io launches open source agentshield against AI agents

Source Decision Insights Record Published October 23, 2026 Companies 4
Human View Machine View

4 companies named across 5 categories, one of 14 articles referencing Solo.io. Previous coverage: Solo.io introduces agentdesktop for agentic governance on desktops (Sep 2026).

Companies mentioned

Best suited for

Seniority
Architect
Job function
Cybersecurity / Security Architect
Persona
Security Architect
Buyer role
Architect / Technical Evaluator
Decision stage
How to start
Adoption curve
Innovators
Technology maturity
Emerging Exploration
Industry
Information Technology / Cybersecurity / Application, Cloud & AI Security / AI Security & LLM/Model Security

Our classification, not the publisher's statement. Best suited for, not only for.

Solo.io has published agentshield, an open source project for protecting the data, APIs, and services an organization already runs from autonomous AI agents it does not control.

Current agent security work centers on identity, guardrails, runtime policy, and human oversight. Those controls function only for agents operating within a control point the organization runs. The largest gap involves agents outside that boundary, including attacker agents, external agents that drift from their intended purpose, and internal agents that escape sandboxes or evade guardrails.

Breach investigations keep finding stolen credentials that still work, permissions no one trimmed, and workloads that reach systems they never needed. Adversaries move from initial foothold to lateral movement in an average of 29 minutes, and in as little as 27 seconds, while AI-enabled adversary operations grew 89 percent year over year, according to CrowdStrike.

Incidents documented this year show autonomous agents reaching cluster-wide administrative access and harvesting thousands of credentials in under six hours from little more than a prompt. The techniques were familiar, but the tempo, persistence, and continuous re-planning were not. Agentshield extends the assume breach premise to assume agent, treating the resource rather than the agent as the unit of protection.

Agentshield offers platform and security teams five capabilities. Plugins instrument existing infrastructure from platform to kernel without changes to the services themselves. A single attack-path graph shows lateral movement and blast radius. Rules are generated from frontier and open source model reasoning at admission time and evaluated at runtime. Findings include severity, affected systems, evidence, and remediation steps.

Remediation can be performed by a human operator moving from dashboard to fix, or by an agent receiving findings as context. The agentshield project provides documentation, a project site, a GitHub repository, and a Discord discussion channel for contributors. It is one of the core open source projects of the Solo.io agentic stack, alongside agentgateway, kagent, agentregistry, agentdesktop, and agentevals.

Press release, provided by Globe Newswire on behalf of Solo.io. Read the original.

Mentions

Structured data (JSON-LD)

The schema.org markup this page publishes for search engines and AI agents, exactly as they read it.

[
  {
    "@context": "https://schema.org",
    "@id": "https://decisioninsights.ai/#website",
    "@type": "WebSite",
    "name": "Decision Insights",
    "potentialAction": {
      "@type": "SearchAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://decisioninsights.ai/search/?q={search_term_string}&submit=1"
      }
    },
    "publisher": {
      "@id": "https://decisioninsights.ai/#organization"
    },
    "url": "https://decisioninsights.ai"
  },
  {
    "@context": "https://schema.org",
    "@id": "https://decisioninsights.ai/#organization",
    "@type": "Organization",
    "contactPoint": {
      "@type": "ContactPoint",
      "contactType": "customer support",
      "email": "[email protected]"
    },
    "description": "Decision Insights is a Registry of technology companies, open source projects, and industry terms, built for people and for AI agents that need sourced, structured information.",
    "logo": {
      "@type": "ImageObject",
      "url": "https://wiretap-cdn-assets.nyc3.cdn.digitaloceanspaces.com/decision-insights/[email protected]"
    },
    "name": "Decision Insights",
    "parentOrganization": {
      "@type": "Organization",
      "name": "Wiretap Labs",
      "sameAs": [
        "https://www.linkedin.com/company/wiretap-labs",
        "https://www.crunchbase.com/organization/wiretap-labs"
      ],
      "url": "https://wiretaplabs.com"
    },
    "publishingPrinciples": "https://decisioninsights.ai/standards/",
    "sameAs": [
      "https://www.linkedin.com/company/decisioninsights"
    ],
    "url": "https://decisioninsights.ai"
  },
  {
    "@context": "https://schema.org",
    "@type": "BreadcrumbList",
    "itemListElement": [
      {
        "@type": "ListItem",
        "item": "https://decisioninsights.ai",
        "name": "Decision Insights",
        "position": 1
      },
      {
        "@type": "ListItem",
        "item": "https://decisioninsights.ai/records/",
        "name": "Records",
        "position": 2
      },
      {
        "@type": "ListItem",
        "item": "https://decisioninsights.ai/solo.io-launches-open-source-agentshield-against-ai-agents/",
        "name": "Solo.io launches open source agentshield against AI agents",
        "position": 3
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "@id": "https://decisioninsights.ai/solo.io-launches-open-source-agentshield-against-ai-agents/#blogposting",
    "@type": "NewsArticle",
    "about": {
      "@id": "https://decisioninsights.ai/registry/solo-io/#organization",
      "@type": "Organization",
      "mainEntityOfPage": "https://decisioninsights.ai/registry/solo-io/",
      "name": "Solo.io"
    },
    "articleSection": [
      "Cybersecurity"
    ],
    "audience": [
      {
        "@type": "Audience",
        "additionalType": "Seniority",
        "audienceType": "Architect"
      },
      {
        "@type": "Audience",
        "additionalType": "Job function",
        "audienceType": "Cybersecurity / Security Architect"
      },
      {
        "@type": "Audience",
        "additionalType": "Persona",
        "audienceType": "Security Architect"
      },
      {
        "@type": "Audience",
        "additionalType": "Buyer role",
        "audienceType": "Architect / Technical Evaluator"
      },
      {
        "@type": "Audience",
        "additionalType": "Adoption curve",
        "audienceType": "Innovators"
      },
      {
        "@type": "Audience",
        "additionalType": "Technology maturity",
        "audienceType": "Emerging Exploration"
      },
      {
        "@type": "Audience",
        "additionalType": "Industry",
        "audienceType": "Information Technology / Cybersecurity / Application, Cloud & AI Security / AI Security & LLM/Model Security"
      }
    ],
    "author": {
      "@id": "https://decisioninsights.ai/author/decision-insights-signals/#person",
      "@type": "Person",
      "name": "Decision Insights Record",
      "url": "https://decisioninsights.ai/author/decision-insights-signals/"
    },
    "dateModified": "2026-10-23T06:21:26-06:00",
    "datePublished": "2026-10-23T06:21:20-06:00",
    "description": "Solo.io introduces agentshield, an open source project that defends existing data, APIs, and services from AI agents that an organization does not control.",
    "headline": "Solo.io launches open source agentshield against AI agents",
    "isBasedOn": {
      "@type": "CreativeWork",
      "sourceOrganization": {
        "@type": "Organization",
        "name": "GlobeNewswire"
      },
      "url": "https://www.globenewswire.com/news-release/2026/10/23/3387213/0/en/solo-io-introduces-agentshield-to-protect-organizations-existing-infrastructure-from-the-ai-agents-they-don-t-control.html"
    },
    "keywords": [
      "AI Agents",
      "Open Source",
      "Remediation",
      "Services"
    ],
    "mainEntityOfPage": {
      "@id": "https://decisioninsights.ai/solo.io-launches-open-source-agentshield-against-ai-agents/",
      "@type": "WebPage",
      "sdDatePublished": "2026-10-23",
      "sdPublisher": {
        "@id": "https://decisioninsights.ai/#organization"
      }
    },
    "mentions": [
      {
        "@id": "https://decisioninsights.ai/registry/crowdstrike/#organization",
        "@type": "Organization",
        "mainEntityOfPage": "https://decisioninsights.ai/registry/crowdstrike/",
        "name": "CrowdStrike"
      },
      {
        "@id": "https://decisioninsights.ai/registry/microsoft/github/#organization",
        "@type": "Organization",
        "mainEntityOfPage": "https://decisioninsights.ai/registry/microsoft/github/",
        "name": "GitHub"
      },
      {
        "@id": "https://decisioninsights.ai/registry/services/#organization",
        "@type": "Organization",
        "mainEntityOfPage": "https://decisioninsights.ai/registry/services/",
        "name": "services"
      },
      {
        "@id": "https://decisioninsights.ai/registry/solo-io/#organization",
        "@type": "Organization",
        "mainEntityOfPage": "https://decisioninsights.ai/registry/solo-io/",
        "name": "Solo.io"
      }
    ],
    "publisher": {
      "@id": "https://decisioninsights.ai/#organization"
    }
  },
  {
    "@context": "https://schema.org",
    "@id": "https://decisioninsights.ai/author/decision-insights-signals/#person",
    "@type": "Person",
    "description": "Press releases and independent analyst research, structured into concise summaries for research and monitoring. Produced under our Standards & Methodology.",
    "name": "Decision Insights Record",
    "sameAs": [
      "https://www.linkedin.com/showcase/decisioninsights/"
    ],
    "url": "https://decisioninsights.ai/author/decision-insights-signals/"
  }
]

Is this your company? Get structured data for your own pages