agentdiscover Alternatives

agentaudit-scanner is an open-source CLI tool that scans AI agent skills, rule files, and MCP configurations for security risks like prompt injections and hidden instructions. It is designed for AI security engineers and developers to ensure safe agent deployments.

agentscanner is an open-source CLI tool that performs static security analysis on agentic AI configuration files, including settings, permissions, hooks, and MCP servers. It helps developers and security teams identify vulnerabilities in AI agent stacks before deployment.

Agent Disco grades a website for AI agents. It checks whether a site is set up for machine use by looking at .well-known/ URIs, llms.txt, robots.txt rules for GPTBot and ClaudeBot, OpenAPI specifications, machine-readable auth docs, and signup barriers, then assigns a grade based on fixed-weight checks. The service presents its checks as structured and readable rather than opaque. Each grade is the sum of fixed-weight checks available at /checks, and failed items include a pointer to the standard being measured plus a specific remediation hint. An example scan shown on the site includes results for crawl.robots_txt, root_level.llms_txt, well_known.ai_plugin_json, and api.openapi_discovery. The site also says the scans are aimed at how easily AI agents can actually use a service. Agent Disco is used on demand: it does not crawl the web continuously, and it only fetches a site when a human submits a URL. The scanner uses one clearly identified User-Agent and a short list of publicly advertised paths, with more information available at /bot. After a scan, users can subscribe to grade-change alerts and receive email when a new scan changes the letter grade or score. The report page also supports auto-rescan on a daily, weekly, or monthly cadence, and the service tracks scan history without requiring CI wiring. It also offers signed JSON webhooks for CI integrations, with examples including pushing grades to a status page, failing a build on regression, or logging to a dashboard. The page includes Log in, Sign up, and Get your API key links, and the footer identifies Starsol Ltd as the company behind the service. The site also lists API among its links. Based on the page text, Agent Disco is an AI-agent discoverability and observability-style scanning tool for website owners and developers who want to check how their sites are understood by AI agents.

Detect if code is running in an AI agent or automated development environment

agentdossier is an open-source Python SDK designed to help developers manage provenance, records, and anchoring for AI agent systems. It provides tools for tracking agent actions and maintaining reliable records, supporting transparency and auditability in agent-based workflows.

agent-diagnostics is an open-source framework for analyzing and annotating the behavior and reliability of coding agents. It provides tools for benchmarking, taxonomy creation, and structured evaluation, helping researchers and developers understand agent performance.

agent-finder is an open-source command-line tool designed to help network administrators discover agents and their identities within complex networks. It supports governance and agent-based protocols, making it useful for environments requiring agent discovery and management.

agentproof-scan is an open-source CLI security scanner designed to probe AI-agent HTTP endpoints for secret and prompt leakage. It integrates with CI pipelines using exit codes to automate security checks, helping developers and security engineers ensure their AI agents are not exposing sensitive information.

agent-debug is an open-source CLI tool for diagnosing failures in AI agent workflows. It provides root cause analysis and actionable fix suggestions, helping AI developers and researchers debug and improve their agent systems.

agentdef is an open-source CLI tool and specification for defining AI agents in a portable, framework-agnostic way. It enables developers to standardize agent definitions and streamline deployment across different AI frameworks.

agent-probe-ai is an open-source CLI tool for adversarial resilience testing of AI agents. It evaluates agent robustness against attacks like memory poisoning and tool misuse, helping AI researchers and security engineers identify vulnerabilities.