litecode · job 77%Kiro · job 76%koda · job 75%wove_2 · job 75%kotef · job 71%local_skills_agent · job 70%qodex · job 75%claudette · job 73%Claude Code · job 76%replicas_dev · job 74%qonqrete · job 76%serf · job 74%nanoagent · job 74%valor · job 74%claude_code_2 · job 75%ocode · job 78%tau_agent · job 72%eve_agent_v2_unleashed · job 81%DeepSeek-Reasonix · job 74%mangopi_cli · job 72%zot · job 77%code_buddy · job 83%agentty · job 78%ollama_local_coding_agent · job 81%carbon_code · job 75%Sandbox Contractor Agent · job 77%grok_build_desktop · job 83%FlashAgent · job 81%Qwen3 Local AI Agent · job 72%Agent Jo · job 75%wcode · job 77%KORA Reach · job 76%Gemma Agents · job 76%OVI-CODE · job 79%aurora_coder · job 75%Junie · job 79%pi · job 77%grinta_coding_agent · job 75%code_assistant · job 72%codentis · job 73%Reika · job 76%qai (local-coding-agent) · job 76%MiniCode Agent · job 83%LLMHIB_CODE (Jenkins) · job 74%Kolega Code · job 76%MiniAgent · job 73%entheai · job 71%optiq_code · job 70%koda_3 · job 73%dscode · job 73%kanzei · job 74%utim_ai · job 78%Numex Codex · job 73%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