roam_code · job 80%siftr · job 77%Codebase Copilot · job 77%sanjaya · job 79%clangaroo · job 76%context_engine · job 81%Gus · job 80%leankg · job 78%fossil_mcp · job 77%codegraff · job 77%lybrary · job 80%Aubade · job 79%CodebaseRAG · job 77%vscode_mcp · job 79%wryneck · job 80%code_memory · job 76%Sourcelens · job 82%Cortex · job 80%mcp-stama · job 77%aptu-coder · job 80%sense · job 78%narsil_mcp · job 80%slnmap · job 75%octocode · job 81%relace_mcp · job 80%tree_sitter_analyzer · job 76%qartez · job 79%ops_codegraph_tool · job 77%rtfm · job 80%mcp_server_vscode · job 78%CICADA · job 81%mcp_ragex · job 82%codehelper · job 83%gograph · job 76%CodeAtlas · job 80%RagPilot · job 82%infrawise · job 78%Claude Context · job 77%sqry · job 80%AtlasBrain · job 85%Bridger · job 82%clangd-mcp · job 77%FileSift · job 78%DeltaContext · job 75%Search Code MCP · job 78%Vera · job 83%SyntaxRAG · job 80%SymForge · job 77%Sonarless MCP · job 76%speedread · job 78%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