agent · handle agentik
deskhand · job 71%gloamy · job 73%deskclaw · job 76%Sageling · job 77%J.A.R.V.I.S. AI API Edition · job 73%Fatiao Agent · job 74%nova · job 76%xharness · job 76%ara · job 73%petclaw_ai · job 81%MacOS AI Agent · job 84%agent_notch · job 81%Jevme · job 74%sam_2 · job 79%Claude Computer Use · job 75%samuel_screen_voice_agent · job 77%pawwork · job 84%Wiyomi · job 84%dorabot · job 73%LKO Mark 3.4 · job 79%abu · job 72%AI Coach · job 81%DullE · job 73%agentic_ai_computer · job 76%ORCA · job 78%Workroom · job 75%Lymora · job 73%Open Interpreter · job 71%Ace · job 71%MarIA · job 77%clicky · job 76%motive · job 70%Aemyos · job 71%screen_voice_agent · job 79%agent_mac · job 77%openworkbuddy · job 81%Verba · job 78%lobsterai · job 72%bolly · job 81%june · job 73%koda_2 · job 74%mac_stats · job 76%boobar · 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