Skip to main content

Monitor and secure AI agents with access control. Detect LangChain, AutoGPT, CrewAI, and more.

Project description

SudoDog

Find and monitor AI agents running on your machine.

pip install sudodog
sudodog-scan
┌─────────────────────────────────────────────────────────┐
│  🐕 SudoDog Shadow Agent Scanner                        │
│     Find AI agents you didn't know were running         │
└─────────────────────────────────────────────────────────┘

Scanning for AI agents...
Checking 142 processes...

============================================================
  SHADOW AGENT SCAN REPORT
============================================================
  Unmonitored Agents Found: 2
============================================================

[1] PYTHON (PID 12847)
    Framework:  langchain
    Confidence: [████████░░] 80%
    Command:    python agent.py --model gpt-4

    Why detected:
      • Framework detected: langchain
      • AI API connections: 1

[2] NODE (PID 9123)
    Framework:  unknown
    Confidence: [██████░░░░] 60%
    Command:    node dist/agent-runner.js

    Why detected:
      • Command matches pattern 'agent'
      • AI API connections: 3

What It Does

  • Scans running processes for AI agent frameworks (LangChain, AutoGPT, CrewAI, etc.)
  • Detects API connections to OpenAI, Anthropic, and other AI providers
  • Works on macOS, Linux, and Windows
  • Zero configuration - just run sudodog-scan

Installation

pip install sudodog

Commands

Scan for AI agents

sudodog-scan              # Quick scan
sudodog-scan --json       # JSON output (for scripts)
sudodog-scan --watch      # Continuous monitoring

Monitor your agents

# Initialize (optional - for dashboard features)
sudodog init

# Run your agent with monitoring
sudodog run python my_agent.py

# Or integrate with Claude Code
sudodog integrate claude-code

Detected Frameworks

Framework Detection Method
LangChain Process args, imports, env vars
AutoGPT Process args, imports
CrewAI Process args, imports
OpenAI Assistants API connections, imports
Anthropic Claude API connections, imports
LlamaIndex Process args, imports
Semantic Kernel Process args, imports

Dashboard (Optional)

See your agents in a web dashboard:

  1. Sign up at dashboard.sudodog.com
  2. Get your API key from Settings
  3. Run: sudodog init and enter your API key
  4. Your scans and monitored agents will appear in the dashboard

Use Cases

  • Security teams: Find unauthorized AI agents in your environment
  • Developers: See what AI tools are running and how much they're costing
  • DevOps: Monitor AI agent health and API usage
  • Compliance: Audit AI agent activity for regulatory requirements

Privacy

Links

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sudodog-2.1.0.tar.gz (36.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sudodog-2.1.0-py3-none-any.whl (45.3 kB view details)

Uploaded Python 3

File details

Details for the file sudodog-2.1.0.tar.gz.

File metadata

  • Download URL: sudodog-2.1.0.tar.gz
  • Upload date:
  • Size: 36.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for sudodog-2.1.0.tar.gz
Algorithm Hash digest
SHA256 b66c9602cf6044adebd8eeb6bcedd1677d7cf82e5957d639990867d5221800c9
MD5 f6d2a65aa7fd71a49f8bb7702ac6c361
BLAKE2b-256 a1605aba30e840fa6cabc0da6314246056e43a4c1f50fe3ee488ab3d591580c0

See more details on using hashes here.

File details

Details for the file sudodog-2.1.0-py3-none-any.whl.

File metadata

  • Download URL: sudodog-2.1.0-py3-none-any.whl
  • Upload date:
  • Size: 45.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for sudodog-2.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0c9d6287d65cb31c57ed7be1a2ef483feda34c1c0abfadfdcbdeb71ce1ddd2f1
MD5 4eff081a6c16188f10aeec81ba264455
BLAKE2b-256 82730d19cfefcdec9ff56e8ea80ff3590332c13160351b28039f6951a341d361

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page