Codescene vs AI Context
Codescene scores 4 points higher — a narrow lead. Read the evidence rows below before treating it as decisive. Both are measured the same way, on the same day, from public evidence only — so this is a comparison of two measurements rather than two marketing pages. How we measure ›
| Codescene | AI Context | what it means | |
|---|---|---|---|
| tashan score | 75 | 71 | upkeep + freshness, gated by adoption |
| Adoption evidence | 2k/wk | 2k/wk | the raw public signal the score came from |
| Last release | active | active | npm publish or repo push |
| Upkeep | 99 | 73 | cadence, maintainers, status |
| Expertise grade | not graded | deep | an LLM read of its own documentation against a fixed rubric |
| Security audit | no known advisories, no build provenance | no known advisories, runs an install script | existence of findings is always free; the detail a licence buys is on each dossier |
| Licence | NOASSERTION | — | |
| Maintainers | more than one | one primary | bus-factor risk |
Install either
Codescene
claude mcp add codescene-codehealth-mcp -- npx -y @codescene/codehealth-mcpAI Context
claude mcp add vibgrate-cli -- npx -y @vibgrate/cliNeither score is a security verdict — "well maintained" and "nothing known is wrong" are different claims, which is why the audit is a separate row and never folded into the number. The full audit for each, including what a licence adds, is on its own page: Codescene · AI Context.