kaban · job 71%doriku · job 74%sudocode · job 74%m1nd · job 73%planwright · job 71%artel · job 72%Butterbase · job 80%forkit · job 71%83blue transfer · job 76%Antigravity MCP Bridge · job 74%threadctx · job 72%agent_enhancer_utilities · job 70%basemouse · job 77%google_antigravity_mcp · job 74%retasc · job 75%bothread · job 78%tasklix · job 73%buggazi · job 72%agents_mcp_gateway · job 71%codegraff · job 79%pi_delegate_mcp · job 75%objective · job 74%codex_mcp_bridge · job 71%OpenContinuity · job 78%Subagent MCP · job 74%Tirith · job 77%toke_local · job 81%Loci Coordination Bus · job 80%AgentDrive · job 74%agentlab_deploy · job 76%RelayFence · job 85%MCP Agent Mail · job 81%LXAgents Shared Instruction · job 76%Local Agent Automation MCP · job 74%multi-agents · job 79%IronShard · job 75%Local RAG · job 74%Schelling Add Forward · job 77%docker-hybrids3 · job 76%dsh-mcp · job 76%Agent Wire · job 75%Hive · job 87%Basemind · job 80%throng-mcp · job 77%agent_orchestrator_2 · job 79%Phase One Big · 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