Context Engine · job 75%local_coding_agent · job 79%gitwhy · job 79%agents_remember · job 84%wisegit · job 81%codebone · job 77%context_engineering · job 76%mimirs · job 84%Koragraph · job 83%srag · job 77%MindCtx · job 83%mcp_memento · job 83%RagPilot · job 83%Pollux · job 80%Skipper · job 77%PMAT · job 76%Acemcp · job 77%indexio · job 80%CodeDiver · job 75%leankg · job 78%speclaw · job 80%RepoContext · job 79%Neuromedia-Repowise · job 78%repobase · job 80%sverklo · job 74%Gus · job 77%sanjaya · job 81%Astra · job 75%repodigest-mcp · job 80%Context Crafter MCP · job 85%Claude Context · job 76%amdb · job 85%Kula · job 75%wryneck · job 84%srclight · job 83%Repo Context MCP · job 87%CookieGli · job 79%qurio · job 78%codemind · job 78%lybrary · job 79%CGIS (Code Graph Intelligence System) · job 80%codehelper · job 80%Sippion · job 84%MCP Repo Tools · job 78%Bridger · job 83%DeltaContext · job 82%Open Kioku · job 83%Cortex · job 86%MIMRY · job 82%Vera · job 81%NervaPack · job 76%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