fuse · job 79%sverklo · job 79%clangaroo · job 76%codenib · job 76%helios · job 78%qartez · job 78%roam_code · job 79%narsil_mcp · job 76%agentmako · job 83%Corulix · job 84%Noulette · job 80%Jev Coding Kit · job 79%slimdex · job 85%omen · job 76%Euthynos · job 81%Jevex · job 78%LOCUS Engine · job 76%Ripple · job 81%pi-mcp · job 81%covdbg · job 76%Basemind · job 82%mysid · job 79%ripwire · job 91%SCS · job 80%Malong LiuHe · job 79%MAW-KG · job 76%RepoContext · job 78%Revelara · job 78%Sourced.dev · job 76%Reliary · job 78%Code Analysis MCP · job 77%pi-coffee · job 79%Gauntlet · job 79%slimread · job 78%Jev Agent Quality · job 84%BlastCode · job 80%RepoSage · job 78%Norma MCP Server · job 80%painpoints · job 79%Mezura · job 76%symvanta · job 76%corbel · job 84%CodeGraph MCP · job 77%Codebase Archaeology MCP · job 81%Chronos-Agent · job 80%4DA MCP Server · job 78%LayerMap · job 88%BSL MCP Analyzer · job 77%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