The Agent Provenance Graph for AI agents — the only memory layer where agents can prove what they knew, trace why they knew it, and coordinate without an LLM in the loop. Timestamped facts. Auditable decisions. Deterministic trust. Ask 'what blocks deploy?' → exact typed answer. Git-style branching. Three memory surfaces: working/semantic/episodic. Decision replay with hindsight bias detection. Conflict detection. Staleness cascade. Utility-weighted edges that self-improve from agent feedback. Agent identity + trust scoring. Time-travel to any past graph state. Works in Cursor, Claude Desktop, LangGraph, any MCP client. Self-hostable. $0 per operation at any scale.

AI代理的来源图谱——唯一允许代理证明其所知、追溯所知原因并无需大模型介入即可协同的内存层。带时间戳的事实、可审计的决策、确定性信任。提问“哪些模块需要部署？”→获得精确的类型化答案。支持Git式分支。三重内存结构：工作记忆、语义记忆、情景记忆。支持带偏见检测的决策回放、冲突检测、陈旧性级联。基于效用加权的边，能从代理反馈中自我优化。代理身份与信任评分。可回溯至任意历史图状态。兼容Cursor、Claude Desktop、LangGraph及任何MCP客户端。支持自托管。任意规模下每项操作成本为零。