Skip to content
    Skip to content
    Gaincontrol
    28CLEAN
    00SCANNING
    00SUSPICIOUS
    00FLAGGED
    Open Source Enterprise Ready
    Quin · AI Agent Scanner

    Nothing in your codebase
    is hidden from Quin.

    Named after Bao Qingtian, the incorruptible judge who saw through every deception. Quin is an open-source CLI that scans any codebase to detect AI agents, extract system prompts, analyze intent, and produce compliance-ready reports.

    View on GitHubEnterprise edition

    See what a scan returns.

    Point Quin at any repository, local or remote. No instrumentation, no agent-side changes — this is the report format the CLI writes to disk.

    Installpip install quin-scanner
    quin-scannerCompleteSample scan
    $quin-scanner scan ./payments-service --output json
    ›resolving target./payments-service
    ›running 13 scannersdependency, config, code-pattern, +10ok
    ›framework detectedCrewAI 0.80.0found
    ›querying OSV.devframework and version onlyok
    ›pass 1/2 classificationagentic_ai · multi_agentok
    ›pass 2/2 synthesis1 agent profiledok
    ›report writtenquin-report.jsonok

    quin-report.json

    {
      "repo_path": "./payments-service",
      "scan_timestamp": "2026-03-30T09:00:00Z",
      "is_ai_application": true,
      "confidence": 0.92,
      "capability_tags": [
        "llm-api", "rag", "multi-agent", "tool-use"
      ],
      "agent_intents": [
        {
          "agent_name": "ResearcherAgent",
          "goal": "Search and synthesize from web sources",
          "capabilities": ["web-search", "summarization"],
          "risk_signals": [
            "has internet access",
            "writes files"
          ]
        }
      ]
    }
    Output from an example repository

    Complete AI agent inventory.
    Zero manual effort.

    Point Quin at any repository, local or remote, and get a structured map of every AI agent, what it's instructed to do, and what risks it carries.

    1. 01

      AI indicator detection

      Scans dependencies, imports, config files, environment variables, and directory structures for signs of AI/ML library usage across any codebase.

    2. 02

      System prompt discovery

      Extracts system prompts from Python source, YAML configs, and prompt template files, surfacing what your agents are actually instructed to do.

    3. 03

      LLM-powered intent analysis

      Sends discovered prompts to an LLM (OpenAI, Anthropic, Google, or Ollama) to summarize each agent's goal, capabilities, and risk signals.

    4. 04

      Structured compliance reports

      Outputs JSON or YAML reports ready for SIEM ingestion, compliance pipelines, or manual security review, with confidence scores and capability tags.

    Supported Languages

    PythonNode.jsGoRustJava+ any AI/ML pattern

    LLM Providers

    OpenAIAnthropicGoogle GeminiOllama (local)--no-llm for heuristics only
    Open Source

    Free forever.
    Self-hosted, no limits.

    Quin's core scanner is MIT-licensed and free to use. Scan local repos, run without LLM analysis, integrate into your own pipelines. Requires Python 3.11+.

    Star on GitHub
    Enterprise Edition

    GitHub org scanning.
    SIEM integration. SSO.

    The enterprise edition adds remote GitHub repo scanning, batch processing, SIEM-ready output, SSO authentication, and a managed dashboard for tracking AI adoption across your entire org.

    Talk to us about Enterprise

    Frequently asked questions

    Thought Leadership

    • 2026-08-22 · 2 min read

      Shadow Agents: The Inventory Problem Nobody's Solved

      Most organizations can't produce a complete list of the AI agents running in their environment. The ones that matter most are the ones nobody registered.

    • 2026-08-18 · 3 min read

      What Is Agentic AI Security?

      "AI security" and "agentic AI security" sound like the same category. They're not. One centers the model; the other centers what the model is authorized to do once it can act.

    • 2026-09-19 · 3 min read

      The Tool Schema Can Lie to You

      A tool schema an agent reads at discovery is a promise, not a contract — nothing in MCP stops a server from serving a different schema by the time that tool is actually called. Checking the call, not the handshake, is what closes the gap.

    Quin surfaces every agent. Aegis governs who acts, Drona orchestrates what they do.

    Pair with Aegis for zero-trust agent governanceOrchestrate safe execution with Drona