The Index · AI & Agents

Amicus vs DeepSeek

These two are level on the tashan score (within 1 points), so the score does not decide it. The evidence rows below are where they differ. 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 ›

AmicusDeepSeekwhat it means
tashan score7069upkeep + freshness, gated by adoption
Adoption evidence2k/wk2k/wkthe raw public signal the score came from
Last releaseactiveactivenpm publish or repo push
Upkeep7381cadence, maintainers, status
Expertise gradesolidsolidan LLM read of its own documentation against a fixed rubric
Security auditno known advisories, runs an install scriptno known advisories, no build provenancea summary — the full audit, free, is on each dossier
LicenceMITMIT
Maintainersone primarymore than onebus-factor risk

Install either

Amicus

claude mcp add amicus -- npx -y amicus

DeepSeek

claude mcp add deepseek-mcp-server -- npx -y deepseek-mcp-server

Neither 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 — the advisory ids, the version that fixes them and anything that runs at install time — is free on its own page: Amicus · DeepSeek.

All ranked AI & Agents ›