← Marketplace degli agenti
Progetto open-source
VibeSearchBench
di VibeBench
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
Scenario:🔍Ricerca e search
928 stelleSelf-host
Skill
Un progetto open-source — esplora il codice e fai il self-host da GitHub.