mcp · handle agentbase
knowledge · job 77%ColdState · job 74%OneDroid Engram · job 76%Lens Serve · job 77%Huda · job 76%Archon-KB · job 75%knowledge_for_agents · job 74%Hivebook - The Knowledge Base for AI Agents · job 80%memsprout · job 78%Agentic-KB · job 79%mitosis · job 75%AgentBay · job 78%neurostack · job 75%knowledge_base_mcp_server · job 80%memento_2 · job 80%Okto Neuron · job 81%songofhawk_doco · job 77%Caos Cerebro · job 79%Reverie · job 77%Spark · job 82%Knoverge · job 76%sunbeam_memory · job 75%Aurelius · job 79%Vist · job 83%Engram + Karpathy LLM Wiki · job 78%trip2g · 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