agent · handle moching
agentic_ai_computer · job 85%Vigil · job 81%OpenHowl · job 77%MDK Tech AI Agent · job 76%Linen · job 71%heliox_os · job 72%my_tiny_agent · job 76%Projet 4, agent IA · job 78%monaw · job 73%screen_voice_agent · job 81%agent_mac · job 76%bunnycompanion · job 72%open_cowork_2 · job 80%AgentBetta · job 80%agent_notch · job 77%b_desktop_companion · job 71%hearth · job 76%Aemyos · job 75%Agent-S · job 77%Operator · job 72%clacky · job 80%dorabot · job 72%LKO Mark 3.4 · job 75%Tamias (栗栗) · job 73%K.I.V.O. · job 75%Cephable · job 77%fuji_web · job 73%Nano-Lumen · job 73%Claude Computer Use · job 81%samuel_screen_voice_agent · job 73%Fan · job 71%JevPilot · job 76%deskhand · job 72%gloamy · job 79%deskclaw · job 75%ORION · job 73%simular_ai · job 77%Zhiyin · job 77%prompt_os · job 74%MacOS AI Agent · job 76%Agente Pessoal · job 71%Fatiao Agent · job 74%Carve · job 72%fluent · job 75%gini_agent · job 71%ORBIT AI Computer Agent · job 76%Raksam AI · job 78%Orbit · job 82%Super Aide · job 76%POK-Agent · job 79%Clearcote Jet · job 75%Sonny Personal Assistant · job 81%Agent KH · job 85%DullE · job 78%AutoComputer · job 71%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series