Skip to content
Back to search

compliant-llm

Build Secure and Compliant AI agents and MCP Servers. YC W23

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/fiddlecube--compliant-llm/badge.svg)](/listings/fiddlecube--compliant-llm)

HTML

<a href="/listings/fiddlecube--compliant-llm"><img src="/api/listings/fiddlecube--compliant-llm/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

# install
pip install compliant-llm

# run the dashboard
compliant-llm dashboard

Configure your LLM provider and run attacks

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 135 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ![Compliant LLM](https://github.com/fiddlecube/compliant-llm/blob/main/docs/images/github.png)
  2. [![PyPI](https://img.shields.io/pypi/dm/compliant-llm?label=pypi%20compliant-llm)](https://pypi.org/project/compliant-llm/)
  3. [![Documentation](https://img.shields.io/badge/Documentation-Read-green?style=flat&logo=github)](https://github.com/fiddlecube/compliant-llm/tree/main/docs)
  4. [![Discord Chat](https://img.shields.io/discord/1376840449167458424?label=chat&logo=discord&color=5865F2)](https://discord.gg/yJuvmj7r)
  5. [![GitHub Stars](https://img.shields.io/github/stars/fiddlecube/compliant-llm?style=flat)](https://github.com/fiddlecube/compliant-llm/stargazers)
  6. [![YC](https://img.shields.io/badge/Y%20Combinator-W23-orange)](https://www.ycombinator.com/companies/fiddlecube)
  7. [![LinkedIn](https://img.shields.io/badge/LinkedIn-Follow-blue?logo=linkedin)](https://www.linkedin.com/company/fiddlecube)
  8. [![Follow on X](https://img.shields.io/twitter/follow/FiddleCubeAI?style=social)](https://twitter.com/fiddlecube)
  9. [![Commit Activity](https://img.shields.io/github/commit-activity/m/fiddlecube/compliant-llm?label=commit%20activity)](https://github.com/fiddlecube/compliant-llm/commits)
  10. [![Issues Closed](https://img.shields.io/github/issues-closed/fiddlecube/compliant-llm)](https://github.com/fiddlecube/compliant-llm/issues?q=is%3Aissue+is%3Aclosed)
  11. ![License](https://img.shields.io/badge/License-MIT-red)
  12. Compliant LLM is your comprehensive toolkit for ensuring compliance and security of your AI systems.
  13. Infosec, compliance, and gen AI teams use compliant-llm to ensure that their AI agents are secure and compliant with internal policies and frameworks like NIST, ISO, HIPAA, GDPR, etc.
  14. It supports multiple LLM providers, and can be used to test prompts, agents, MCP servers and GenAI models.
  15. Go through our [documentation](https://github.com/fiddlecube/compliant-llm/tree/main/docs) for more details.
  16. [![Report a Bug](https://img.shields.io/badge/Report%20a%20Bug-GitHub-red?style=flat&logo=github)](https://github.com/fiddlecube/compliant-llm/issues/new?assignees=&labels=bug&template=bug_report.md&title=%5BBUG%5D+)
  17. [![Request a Feature](https://img.shields.io/badge/Request%20a%20Feature-GitHub-blue?style=flat&logo=github)](https://github.com/fiddlecube/compliant-llm/issues/new?assignees=&labels=feature&template=feature_request.md&title=%5BFEATURE%5D+)
  18. ## 🎯 Key Features
  19. - 🎯 **Security Testing**: Test against 8+ attack strategies including prompt injection, jailbreaking, and context manipulation
  20. - 📊 **Compliance Analysis**: Ensure the compliance of your AI systems against NIST, ISO, OWASP, GDPR, HIPAA and other compliance frameworks
  21. - 🤖 **Provider Support**: Works with multiple LLM providers via LiteLLM
  22. - 📈 **Visual Dashboard**: Interactive UI for analyzing test results
  23. - ⚡ **End to End Testing**: Test your AI systems end to end
  24. - 📄 **Detailed Reporting**: Comprehensive reports with actionable insights
  25. ## ⚙️ Install and Run
  26. ```bash
  27. # install
  28. pip install compliant-llm
  29. # run the dashboard
  30. compliant-llm dashboard
  31. ```
  32. Configure your LLM provider and run attacks
  33. ![](docs/gif/demo.gif)
  34. ## Support
  35. [![Create Issue](https://img.shields.io/badge/Create-Issue-blue?style=flat&logo=github)](https://github.com/fiddlecube/compliant-llm/issues/new/choose)
  36. Contact: founders@fiddlecube.ai
  37. Meet: 🔗 [Find a slot](https://cal.com/kaushiks/fc)
  38. Community: 💬 [Discord](https://discord.gg/yJuvmj7r), [X](https://x.com/FiddleCubeAI), [LinkedIn](https://www.linkedin.com/company/fiddlecube/)
  39. ## Self-hosted or hosted cloud: Book a demo
  40. 🔗 [Book a slot](https://cal.com/kaushiks/fc)
  41. ## Supported Providers
  42. - OpenAI
  43. - Anthropic
  44. - Gemini
  45. - Mistral
  46. - Groq
  47. - Deepseek
  48. - Azure
  49. - vLLM Ollama
  50. - Ollama
  51. - Nvidia Nim
  52. - Meta Llama
  53. ## Roadmap
  54. - [ ] Full Application Pen Testing
  55. - [ ] Compliant and Logged MCP Servers
  56. - [ ] Support different Compliance Frameworks - NIST, HIPAA, GDPR, EU AI Act, etc.
  57. - [ ] Multimodal Testing
  58. - [ ] CI/CD
  59. - [ ] Access Control checks
  60. - [ ] Control Pane for different controls
  61. - [ ] Internal audits and documentation
  62. ## ⭐️ Star us
  63. ![](docs/gif/stars.gif)
  64. ## 🤝 Contributors
  65. | Developers | Contributors |
  66. |------------|--------------|
  67. | Those who build with `compliant-llm`. | Those who make `compliant-llm` better. |
  68. | (You have `import compliant-llm` somewhere in your project) | (You create a PR to this repo) |
  69. We welcome contributions from the community! Whether it's bug fixes, feature additions, or documentation improvements, your input is valuable.
  70. 1. Fork the repository
  71. 2. Create your feature branch (git checkout -b feature/AmazingFeature)
  72. 3. Commit your changes (git commit -m 'Add some AmazingFeature')
  73. 4. Push to the branch (git push origin feature/AmazingFeature)
  74. 5. Open a Pull Request
  75. ## 🔒 Security & Privacy
  76. We take data security and privacy seriously. Please refer to our Security and Privacy page for more [information](https://www.fiddlecube.ai/privacy-policy).
  77. ### Telemetry
  78. Compliant LLM tracks anonymized usage statistics to improve the product.
  79. No private or personally identifiable information is tracked.
  80. You can opt-out by setting `export DISABLE_COMPLIANT_LLM_TELEMETRY=true`.
  81. ## 📝 Cite Us
  82. `@misc{compliant_llm2025,
  83. author = {FiddleCube},
  84. title = {Compliant LLM: Build Secure AI agents and MCP Servers},
  85. year = {2025},
  86. howpublished = {\url{<https://github.com/fiddlecube/compliant-llm}}>,
  87. }`
  88. <!-- Place this tag in your head or just before your close body tag. -->

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.