Keryn and Endor Labs
Endor Labs is an application security platform built around dependency reachability.
Every row links the source it comes from (how these pages are written). Vendor statements quote the vendor’s own pages as read on 18 November 2026; products change, so follow the link before relying on a row. A missing row is not a claim that the vendor lacks something.
What they do
Section titled “What they do”| Claim | Source |
|---|---|
| Reachability that traces “exploitability across direct and transitive dependencies down to the specific vulnerable function”. | Endor Labs: reachability |
| AI static analysis that “combines pattern matching, dataflow analysis, and multi-pass LLM reasoning”. | Endor Labs: AI SAST |
| An inventory of “coding agents, models, MCP servers, skills, and hooks” with policy on agent actions. | Endor Labs: coding agent governance |
Where they are stronger
Section titled “Where they are stronger”| Claim | Source |
|---|---|
| Reachability across many languages and transitive dependencies, packaged for CI. | Endor Labs: reachability |
Where Keryn differs
Section titled “Where Keryn differs”| Claim | Source |
|---|---|
| Keryn follows model output into code and tools in the application itself, with a proof level per finding. | Why the edges |
| Keryn’s rule-based findings are deterministic from the same evidence. | Scores |
Measured results for Keryn are on the evaluations page, with what each one does not show.