38 free, vendor-neutral tools to find, assess and control AI use, and 16 more for developers building with AI. No signup needed.
What the grades mean
Grades come from published facts: training on your data, retention, admin controls, SSO, certifications and data location. See how we score.
Added and reviewed: Tabnine does not train on your code and keeps zero code retention.
Added and reviewed: Amazon Q Developer Pro does not train on your content; Free tier is opt-out.
Added and reviewed: DeepL Pro does not store or train on your texts; SSO with SAML; SOC 2 Type II.
Added and reviewed: Free DeepL may use your texts for training.
Added and reviewed: Gamma trains on individual plans unless you opt out; never on Business and Enterprise.
18 Nov 2026, OWASP LLM01
Indirect prompt injection through shared calendar invites
16 Nov 2026, OWASP LLM03
Typosquatted MCP server packages steal developer secrets
13 Nov 2026, OWASP LLM02
AI meeting notes shared with external guests by default
Find out which AI is in use and whether it is safe.
Check files, text and configs before an AI reads them.
Harden and test the AI apps and agents you build.
Policies, inventories, assessments and compliance.
Everyday tools for developers building with LLM APIs: tokens, prices, prompts, schemas, evals and errors.