发表机构
Peak Summit Labs（峰汇实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出PrimeAgentOrchestrator系统，生成预加载用户个人数据库相关记忆的Claude Code实例，并行查询两类记忆后端融合结果，管理智能体全生命周期，经四个月部署记录相关机制与工程权衡。
AI 中文摘要
大语言模型（LLM）编码智能体在每次会话开始时都会清空上下文窗口，丢弃之前工作中积累的知识。我们提出PrimeAgentOrchestrator（PAO），这是一个生成Claude Code（Anthropic基于终端的编码智能体）新实例的系统，这些实例预加载了从用户现有个人数据库中编译的相关记忆。在生成时，PAO并行查询两个独立运行的记忆后端（PostgreSQL实体-观测数据库和Cloudflare Worker语义搜索索引），使用特定于后端的检索策略融合结果，并通过利用主机智能体配置自动读取行为的文件系统注入传递编译后的简报。PAO管理完整的智能体生命周期，包括信任预植入、带错误检测的就绪轮询以及自适应终端文本注入。我们报告了2025年12月至2026年3月四个月的常规部署情况，作为经验报告，记录了三代上下文传递机制、促使每次重新设计的故障模式，以及桥接异构记忆系统而非构建统一系统的工程权衡。
英文摘要
Large language model (LLM) coding agents start each session with an empty context window, discarding accumulated knowledge from prior work. We present PrimeAgentOrchestrator (PAO), a system that spawns new instances of Claude Code -- Anthropic's terminal-based coding agent -- pre-loaded with relevant memories compiled from the user's existing personal databases. At spawn time, PAO queries two independently-operated memory backends in parallel (a PostgreSQL entity-observation database and a Cloudflare Worker semantic search index), fuses results using backend-specific retrieval strategies, and delivers the compiled briefing via filesystem injection that exploits the host agent's configuration auto-read behavior. PAO manages the full agent lifecycle including trust pre-seeding, readiness polling with error detection, and adaptive terminal text injection. We report on four months of regular deployment (December 2025 through March 2026) as an experience report, documenting three generations of context delivery mechanisms, the failure modes that motivated each redesign, and the engineering tradeoffs of bridging heterogeneous memory systems rather than building a unified one.
Comments10 pages, 15 references, experience report
