agent · handle winkterm
gptme · job 80%mimo_code · job 83%OpenCode · job 76%adal · job 77%seek · job 75%pi_agent_rust · job 78%Agent-S · job 72%pi · job 72%claudette · job 70%clavue · job 73%claudeme · job 78%nebushell · job 76%acolyte · job 81%zai_shell · job 78%zero_terminal_agent · job 82%klyxor · job 80%openphoenix · job 79%aish · job 72%termu · job 72%kimix · job 72%clawcodex · job 81%openseek · job 72%OpenTerminal · job 80%Dropstone · job 80%CoreCLI · job 77%OpenCrabs · job 72%project_golem · job 74%grok_build_desktop · job 74%claude_code_2 · job 73%jcode · job 79%uniterm · job 76%heliox_os · job 73%athena_code · job 79%waylou · job 74%pawwork · job 72%Mindfork · job 78%tilde · job 80%smallest_agent · job 79%smol · job 78%Talos · job 79%gogogot · job 77%agent-go · job 81%Oscar · job 78%micro-pa · job 73%Kana · job 73%MarIA · job 79%ECAssistant Console · job 80%wcode · job 77%tuskbot · job 79%utim_ai · job 74%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