ContextStream · job 75%Lightrun · job 76%Ref · job 77%repobase · job 75%mcp_docs_provider · job 75%opentrace · job 76%mnemo · job 73%mode_manager_mcp · job 79%infrawise · job 75%rtfm · job 75%fathom · job 73%codemem · job 81%srclight · job 77%codehelper · job 82%codemind · job 76%gortex · job 75%amdb · job 83%sense · job 75%gnosis_mcp · job 80%local_coding_agent · job 77%lybrary · job 79%heimdall_mcp_server · job 78%contextmcp · job 74%ctx_4 · job 73%CodeAtlas · job 79%KnowledgeRail · job 74%Repo Context MCP · job 79%leankg · job 75%Pollux · job 79%TokenArchive · job 75%sourcebook · job 75%Koragraph · job 75%lybrary_2 · 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