AI Security

AI and LLM Security

Test and defend models, prompts, agents and the infrastructure around them.

45 tools profiled

How it differs Tests and guards models, LLM applications and agents against prompt injection, jailbreaks and data leakage. Scanning an AI app's own code is still SAST or SCA.

License
Subcategory
Deployment
Languages
Integrations
Maturity
Signals

45 tools

  • Rebuff

    Protect AI

    AI Security

    Open source prompt injection detector that layers heuristics, a classifier prompt, a vector store of known attacks and canary tokens.

    Open source
    Emerging
  • Alter

    Alter

    AI Security

    Commercial product in the AI security category addressing identity and access control for AI agents.

    Commercial
    Emerging
  • AI Security

    Toolkit for defining rails on an LLM conversation using a dedicated modeling language, controlling input, output, topic, retrieval and tool execution.

    Open source
    Growing
  • Lakera Guard

    Lakera

    AI Security

    Detection API that classifies prompts and model outputs for injection, jailbreak attempts, sensitive data and policy violations before they land.

    Commercial, free tier
    Growing
  • AI Security

    Open source project from Cisco's AI Defense group addressing security controls for AI agent and LLM application activity.

    Open source
    Emerging
  • Arize AI

    Arize AI

    AI Security

    LLM and ML observability platform that captures application traces and runs evaluations over them, with an open source tracing and evaluation component.

    Open source and commercial
    Established
  • Runlayer

    Runlayer

    AI Security

    Commercial control layer for AI agent tool access, mediating connections between agents and the systems they act on.

    Commercial
    Emerging
  • Protect AI Guardian

    Protect AI

    AI Security

    Scanning gateway for machine learning model files that inspects serialized artifacts for executable payloads and enforces policy on what may be pulled.

    Commercial
    Growing
  • 7AI

    7AI

    AI Security

    Platform that applies AI agents to security operations work such as alert triage, phishing analysis and exposure investigation.

    Commercial
    Emerging
  • Holistic AI

    Holistic AI

    AI Security

    AI governance platform for inventorying models, assessing risk against regulatory frameworks and running bias audits on automated decision systems.

    Commercial
    Growing
  • Guardrails AI

    Guardrails AI

    AI Security

    Python framework that wraps LLM calls in composable validators and decides what to do when a prompt or a response fails one.

    Open source and commercial
    Growing
  • Galileo AI

    Galileo

    AI Security

    Evaluation and observability platform for LLM and agent applications, with purpose built scoring models and an inline guardrail path.

    Commercial
    Growing
  • Rebuff

    Protect AI

    Open source prompt injection detector that layers heuristics, a classifier prompt, a vector store of known attacks and canary tokens.

    Open source Emerging
    AI Security
  • Alter

    Alter

    Commercial product in the AI security category addressing identity and access control for AI agents.

    Commercial Emerging
    AI Security
  • Toolkit for defining rails on an LLM conversation using a dedicated modeling language, controlling input, output, topic, retrieval and tool execution.

    Open source Growing
    AI Security
  • Lakera Guard

    Lakera

    Detection API that classifies prompts and model outputs for injection, jailbreak attempts, sensitive data and policy violations before they land.

    Commercial, free tier Growing
    AI Security
  • Open source project from Cisco's AI Defense group addressing security controls for AI agent and LLM application activity.

    Open source Emerging
    AI Security
  • Arize AI

    Arize AI

    LLM and ML observability platform that captures application traces and runs evaluations over them, with an open source tracing and evaluation component.

    Open source and commercial Established
    AI Security
  • Runlayer

    Runlayer

    Commercial control layer for AI agent tool access, mediating connections between agents and the systems they act on.

    Commercial Emerging
    AI Security
  • Protect AI Guardian

    Protect AI

    Scanning gateway for machine learning model files that inspects serialized artifacts for executable payloads and enforces policy on what may be pulled.

    Commercial Growing
    AI Security
  • 7AI

    7AI

    Platform that applies AI agents to security operations work such as alert triage, phishing analysis and exposure investigation.

    Commercial Emerging
    AI Security
  • Holistic AI

    Holistic AI

    AI governance platform for inventorying models, assessing risk against regulatory frameworks and running bias audits on automated decision systems.

    Commercial Growing
    AI Security
  • Guardrails AI

    Guardrails AI

    Python framework that wraps LLM calls in composable validators and decides what to do when a prompt or a response fails one.

    Open source and commercial Growing
    AI Security
  • Galileo AI

    Galileo

    Evaluation and observability platform for LLM and agent applications, with purpose built scoring models and an inline guardrail path.

    Commercial Growing
    AI Security
  • WhyLabs

    WhyLabs

    AI Security

    Observability platform for ML and LLM systems built on lightweight statistical profiles, with drift monitoring and text quality and safety metrics.

    Open source and commercial
    Established
  • Straiker

    Straiker

    AI Security

    Commercial AI security platform pairing automated adversarial testing of AI applications with runtime inspection of prompts and responses.

    Commercial
    Emerging
  • AI-Infra-Guard

    Tencent

    AI Security

    Open source scanner that fingerprints self hosted AI infrastructure components and matches them against known vulnerabilities, with an MCP server analysis mode.

    Open source
    Emerging
  • Promptfoo

    Promptfoo

    AI Security

    Config driven test and red team harness for LLM applications, running assertions and generated adversarial probes against prompts, models and agents.

    Open source and commercial
    Growing
  • Future AGI

    Future AGI

    AI Security

    Evaluation and observability platform for LLM applications, combining offline scoring of model output with runtime checks on inputs and responses.

    Freemium
    Emerging
  • DeepTeam

    Confident AI

    AI Security

    Open source Python framework that generates adversarial prompts against an LLM application and scores the responses for vulnerabilities such as bias, PII leakage and excessive agency.

    Open source
    Growing
  • Cerbos

    Cerbos

    AI Security

    Decoupled authorization engine that evaluates YAML policies over a principal, resource and action and returns an allow or deny decision over an API.

    Open source and commercial
    Established
  • Adversarial Robustness Toolbox (ART)

    Linux Foundation AI & Data

    AI Security

    Python library implementing adversarial attacks and defenses against machine learning models, covering evasion, poisoning, extraction and inference.

    Open source
    Established
  • NeuralTrust

    NeuralTrust

    AI Security

    AI gateway that inspects and enforces policy on LLM traffic, paired with adversarial testing and conversation observability.

    Commercial
    Emerging
  • Mindgard

    Mindgard

    AI Security

    Runs a library of AI attacks against your deployed models through their normal interface and reports which ones succeeded.

    Commercial
    Growing
  • Lasso Security

    Lasso Security

    AI Security

    GenAI security platform covering discovery of AI tools in use, inspection of prompts and responses, and controls on what data reaches a model.

    Commercial
    Emerging
  • Knostic

    Knostic

    AI Security

    Detects where enterprise AI assistants expose data users should not reach, and maps the permission mistakes behind each exposure.

    Commercial
    Emerging
  • WhyLabs

    WhyLabs

    Observability platform for ML and LLM systems built on lightweight statistical profiles, with drift monitoring and text quality and safety metrics.

    Open source and commercial Established
    AI Security
  • Straiker

    Straiker

    Commercial AI security platform pairing automated adversarial testing of AI applications with runtime inspection of prompts and responses.

    Commercial Emerging
    AI Security
  • AI-Infra-Guard

    Tencent

    Open source scanner that fingerprints self hosted AI infrastructure components and matches them against known vulnerabilities, with an MCP server analysis mode.

    Open source Emerging
    AI Security
  • Promptfoo

    Promptfoo

    Config driven test and red team harness for LLM applications, running assertions and generated adversarial probes against prompts, models and agents.

    Open source and commercial Growing
    AI Security
  • Future AGI

    Future AGI

    Evaluation and observability platform for LLM applications, combining offline scoring of model output with runtime checks on inputs and responses.

    Freemium Emerging
    AI Security
  • DeepTeam

    Confident AI

    Open source Python framework that generates adversarial prompts against an LLM application and scores the responses for vulnerabilities such as bias, PII leakage and excessive agency.

    Open source Growing
    AI Security
  • Cerbos

    Cerbos

    Decoupled authorization engine that evaluates YAML policies over a principal, resource and action and returns an allow or deny decision over an API.

    Open source and commercial Established
    AI Security
  • Adversarial Robustness Toolbox (ART)

    Linux Foundation AI & Data

    Python library implementing adversarial attacks and defenses against machine learning models, covering evasion, poisoning, extraction and inference.

    Open source Established
    AI Security
  • NeuralTrust

    NeuralTrust

    AI gateway that inspects and enforces policy on LLM traffic, paired with adversarial testing and conversation observability.

    Commercial Emerging
    AI Security
  • Mindgard

    Mindgard

    Runs a library of AI attacks against your deployed models through their normal interface and reports which ones succeeded.

    Commercial Growing
    AI Security
  • Lasso Security

    Lasso Security

    GenAI security platform covering discovery of AI tools in use, inspection of prompts and responses, and controls on what data reaches a model.

    Commercial Emerging
    AI Security
  • Knostic

    Knostic

    Detects where enterprise AI assistants expose data users should not reach, and maps the permission mistakes behind each exposure.

    Commercial Emerging
    AI Security
Tick up to 4 tools above.