retasc · job 80%Sol–Luna Orchestrator · job 79%Tianshu MCP · job 81%MCP Agent Mail · job 76%watercooler · job 78%FableFlow · job 74%tasklix · job 74%Tirith · job 79%pi_delegate_mcp · job 75%Meridian · job 80%Agent Cowork Memory · job 77%Vibe Engineering MCP · job 76%ZergSwarm · job 74%session-hub · job 74%Project Desk · job 73%pi-coffee · job 80%Starfix · job 77%AgentDrift · job 77%fixter · job 76%Plannotator Inbox · job 74%agentchan · job 75%mcptask · job 75%agentic_ecos · job 73%Loci Coordination Bus · job 83%doriku · job 82%sprawl · job 81%Herdr Mesh Safe · job 74%bothread · job 75%hythe · job 79%objective · job 79%Project Relay · job 79%Passalong · job 76%kanbo · job 75%stele · job 82%Bellek · job 78%Context Cockpit · job 76%CrewChat · job 78%AgentKanban · job 76%hamloy · job 77%Prompt Optimizer · job 73%magents · job 77%subtask · job 76%Basemind · job 82%throng-mcp · job 78%dsh-zcode-bridge · job 73%Effort · job 78%Aaly · job 76%Tower · job 76%Agent Decision Kit · job 75%RelayFence · job 79%pizzadeveloper · job 78%Task Journal · job 75%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