ternlang · job 77%computesdk · job 73%litellm_agent_platform · job 73%Claw Code · job 82%opensandbox · job 73%TalkCody · job 74%xcode_mcp_wrapper · job 75%mcp_memory_gateway_v2 · job 74%massgen · job 73%Lightrun · job 75%Together Code Interpreter MCP Server · job 72%morph · job 74%mk_family · job 81%architect_mcp_server · job 78%mcp_workspace · job 73%glass · job 79%dotbot · job 76%agent_tool · job 80%trueline_mcp · job 74%shrimp_task_manager · job 79%coding_tools_mcp · job 77%wcgw · job 76%terminal_mcp · job 75%freya_mcp_server · job 82%local_coding_agent · job 80%cpp-analysis-mcp · job 78%Agent Env MCP · job 76%GenPark In-Process Python REPL Skill · job 74%LOCUS Engine · job 80%pi-mcp · job 82%python_code_validator · job 76%GenPark Safe Tool Execution Isolation Containment Skill · job 74%coding_tools_mcp_2 · job 74%Editor MCP · job 81%Code Relay · job 77%mistle · 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