Skip to content
BYOK Tools

Methodology

The Key Safety Score

A 0 to 100 rating of how well an app protects the API key you give it. Rules-based, published and applied to every listing.

Scoring rubric

FactorMaxScoring
Key storage40Local (on-device, direct to provider) 40. Vendor server 18. Undocumented 10.
Auditable code25Open source 25. Closed source 0.
Self-hosting15Self-hostable service 15. Local desktop, CLI or editor app 8. Vendor-hosted web app 0.
Offline option10Supports local models (Ollama, LM Studio) 10.
Provider choice102 points per supported provider, up to 10.

Grades: A is 80 or above, B is 60 to 79, C is 40 to 59, D is below 40. The score covers key handling only. It is not a security audit and says nothing about output quality. Inputs come from public documentation, source code where available, and our own testing. Makers can submit corrections.

A

190 tools

B

95 tools

C

6 tools

D

7 tools

Highest scoring tools

  1. 1
    LobeChat (LobeHub) · Chat Clients100
  2. 2
    SillyTavern · Creative & Roleplay100
  3. 3
    AnythingLLM · Notes & Knowledge100
  4. 4
    big-AGI · Chat Clients100
  5. 5
    CrewAI · Automation & Agents100
  6. 6
    GPT Researcher · Research & Search100
  7. 7
    marimo · Coding Agents & IDEs100
  8. 8
    NextChat · Chat Clients100
  9. 9
    PDFMathTranslate · Translation100
  10. 10
    bolt.diy · Coding Agents & IDEs100
  11. 11
    Browser Use · Automation & Agents100
  12. 12
    Jupyter AI · Coding Agents & IDEs100
  13. 13
    Next AI Draw.io · Creative & Roleplay100
  14. 14
    OpenClaw · Automation & Agents100
  15. 15
    Plandex · Coding Agents & IDEs100
  16. 16
    ONLYOFFICE AI Agent · Writing100
  17. 17
    Project AIRI · Creative & Roleplay100
  18. 18
    Refact.ai · Coding Agents & IDEs100
  19. 19
    VideoLingo · Translation100
  20. 20
    Word GPT Plus · Writing100