mcp · handle slm_mesh
multi-agents · job 84%ai-crew-sync · job 86%agentcouch · job 78%chatroom-mcp · job 81%Marshal · job 85%collide · job 77%agent-peers · job 76%Bellek · job 82%hythe · job 76%Okto Nexus · job 78%retasc · job 85%agent-watercooler · job 81%agent-mailbox · job 76%Kilo-Kit · job 81%Join.Cloud · job 76%Commons · job 81%Meshingly MCP · job 78%board_mcp · job 80%Docket · job 85%AgentMBX · job 79%Kashkeshet · job 76%agent_orchestration · job 83%agentbus · job 78%Meridian · job 88%Tower · job 83%agent_mesh · job 77%Starfix · job 87%doriku · job 87%bothread · job 78%MCP Session Share · job 80%Partyline · job 92%objective · job 84%Agent Work MCP · job 78%minymaton · job 81%Swarm MCP Server · job 89%GenPark Blackboard Shared State Sync · job 77%GenPark Blackboard Architecture Shared Memory Skill · job 80%Context Cockpit · job 80%Relay · job 77%CrewChat · job 88%artel · job 81%hamloy · job 80%MCP Agent Bus · job 85%Concord MCP · job 80%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