doriku · job 75%openclaude · job 73%mistle · job 72%Undisk MCP · job 80%Cline · job 73%Claw Code · job 77%Kilo · job 71%gitwhy · job 74%sift · job 73%bitbucket · job 77%Filesystem MCP Server · job 75%MCP Interactive Editor · job 71%watercooler · job 71%RepoContext · job 76%DeployIt · job 75%LOCUS Engine · job 74%speclaw · job 74%filesystem-mcp · job 72%coding_tools_mcp · job 81%trueline_mcp · job 79%codescout · job 77%toke_local · job 73%repo_bridge · job 71%coding_tools_mcp_2 · job 78%patchloom · job 74%p4mcp_server · job 72%git_courer · job 78%domscribe · job 73%mcp_workspace · job 72%desktop_commander_mcp · job 71%selvedge · job 71%objective · job 73%agents_remember · job 79%local_coding_agent · job 78%pi-mcp · job 77%GitWarren · job 76%Tokenectomy Git · job 75%MCP GitHub Repository Orchestrator · job 75%Koragraph · job 74%mcp_memento · job 73%sync · job 75%Editor MCP · job 76%Context Crafter MCP · 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