Skip to content
Back/Harness Engineering

Agent Memory Engineering(Nic)

View in Graph
Updated 2026-10-29
1 min read
196 words

Agent Memory Engineering

This page is now a source reference for Nic’s memory-system audit. The primary reusable concept extracted from it is Agent Memory as Hint Surface.

Search terms preserved here: Hermes memory, Codex memory, Claude Code memory, MEMORY.md, memory_summary.md, prefix cache, simple stack wins, LLM + Markdown + bash, index always visible, lazy body, verify on read, signal gate, persistent prompt injection.

Key source claims

  • Simple memory stacks often beat vector DB / graph / background-agent architectures in daily agent workflows.
  • Prompt-cache economics strongly shape memory injection design.
  • Memory writes need signal gates; memory reads need freshness and verification discipline.
  • Agent memory is model-harness fit, not just portable bytes.

2026-10:codebase-as-agent-memory 双杠杆

来源:AI Briefing 2026-10-13

poteto 的两个杠杆:①让 agent 自我验证——验证产物先行,人审证据而非 diff;②把代码库当作 agent 的持久记忆——重复错误编码为类型/测试/lint 约束而非更长提示词(失败→约束,对应 trust-ladder 的"环境改进"层)。

2026-10-29:预先整理的 Markdown Vault

@Mr_Buzzoni 的 X Article 将两篇十月研究归纳为:在提问前先把原始资料整理成互链文件;由强模型负责写入知识库,较便宜的 worker 负责常见读取和路由。文章也建议用 CLAUDE.md 约束剪藏内容,并将记忆保存在普通 Markdown 文件中。这里记录的是作者对论文的转述,尚未直接核验原始论文。

Sources (addendum)

Pending Jean review

Sources

Synthesized from 3 sources
  • Agent Memory EngineeringSupporting source listed by this page.Whole pagemediumbody
  • 2026-10-13-18-11Supporting source listed by this page.Whole pagemediumabsorb log
  • 2026-10-29-21-16Supporting source listed by this page.Whole pagemediumabsorb log

Evolution

1 event
  1. absorbed

    Derived from source material

    This page is currently synthesized from 3 sources.

    From Agent Memory Engineering, 2026-10-13-18-11, 2026-10-29-21-16To Agent Memory Engineering(Nic)
    Sources: raw/to-learn/Agent Memory Engineering.md · raw/briefing/AI Briefing/2026-10-13-18-11.md · raw/briefing/AI Briefing/2026-10-29-21-16.md

Linked from