agent · handle pocket_lobster_android
gptme · job 75%clavue · job 73%Agent-S · job 73%pi_agent_rust · job 78%firebender · job 76%PatchDesign · job 77%golem · job 78%TermuxAI · job 75%abaopal · job 77%PlugClaw · job 75%appclaw · job 80%nemo_code · job 75%aiope · job 79%opendroid · job 78%claude_code_2 · job 77%agentty · job 76%omni · job 75%formax · job 74%grok_build_desktop · job 74%tau_agent · job 70%jcode · job 74%zot · job 73%aurix_agent · job 73%Sandbox Contractor Agent · job 72%mimo_code · job 72%kodacode · job 73%mangopi_cli · job 71%jenny · job 76%opengui · job 76%foneclaw · job 76%autoxiaoer · job 75%acolyte · job 73%4ais · job 77%ocode · job 76%zyraxon_ai · job 75%topoclaw · job 72%code_buddy · job 76%azmx_ai · job 75%standard_code · job 77%microcodex · job 76%shelley · job 75%utim_ai · job 73%dsh-mini · job 80%DroidPilot · job 81%Lemonade Agent · job 78%Codaki Mini Codex · job 73%DOT · job 76%豆糕 DouGao · job 75%Sidekick · job 73%pokeclaw · job 80%OpenCyvis Phone · job 74%Termux-Dev · job 84%Reasonix Desktop · job 76%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