Adam Framework
AI Amnesia — Solved. Within-Session Coherence Degradation — Solved.
The Adam Framework is a 5-layer persistent memory architecture for OpenClaw agents, developed over 8 months across 353 sessions on a live business by a non-coder running consumer hardware.
OpenClaw just got acquired by OpenAI. Your memory layer shouldn't be.
What It Solves
- - AI Amnesia — your agent wakes up blank every session, forcing you to re-explain context, projects, and goals that should already be known
- Within-Session Drift — as a session accumulates context, the model's reasoning consistency quietly degrades before compaction triggers
The 5 Layers
| Layer | Component | What It Does |
|---|
| 1 | Vault injection via SENTINEL | Identity files loaded at every boot. Agent wakes up knowing who it is. |
| 2 |
memory-core plugin | Live memory search mid-session via memory
search / memoryget tools |
| 3 | Neural graph (nmem_context) | Associative recall — 12,393 neurons, 40,532 synapses. Concepts link to concepts. |
| 4 | Nightly reconciliation | Gemini merges daily logs into CORE_MEMORY.md while you sleep. Nothing lost. |
| 5 | Coherence monitor | Scratchpad dropout detector — fires re-anchor before drift causes damage. 33 tests passing. |
The Key Insight
The memory is in the files. The model is just the reader.
When the system was completely wiped and rebuilt from scratch, the agent came back online with full continuity — because the identity files survived. Swap the LLM, keep the Vault. Memory persists.
Setup
Two paths — pick one:
Path 1 — You do it yourself (30–60 min)
Read SETUP_HUMAN.md. Plain English, no technical background assumed.
Path 2 — Let your agent handle it
Paste SETUP_AI.md into your OpenClaw chat. It asks 8 questions and does the install itself.
Prerequisites
- - OpenClaw running with any model
- Python 3.10+
- INLINECODE0
- NVIDIA Developer free tier API key (Kimi K2.5, 131K context, free)
- Gemini API key (free) for nightly reconciliation
Links
- - Repo: https://github.com/strangeadvancedmarketing/Adam
- Live proof (353 sessions): https://strangeadvancedmarketing.github.io/Adam/showcase/ai-amnesia-solved.html
- Full setup guide: https://github.com/strangeadvancedmarketing/Adam/blob/master/SETUP_HUMAN.md
Adam框架
AI失忆症——已解决。会话内连贯性退化——已解决。
Adam框架是一个面向OpenClaw代理的五层持久化记忆架构，由一位非程序员在消费级硬件上，历经8个月、353次会话，基于真实业务场景开发而成。
OpenClaw刚被OpenAI收购。但你的记忆层不该被收购。
解决的问题
- - AI失忆症——你的代理每次会话都从空白状态启动，迫使你重新解释本应已知的上下文、项目和目标
- 会话内漂移——随着会话积累上下文，模型推理一致性会在压缩触发前悄然退化
五层架构
| 层级 | 组件 | 功能 |
|---|
| 1 | 通过SENTINEL注入Vault | 每次启动时加载身份文件。代理醒来就知道自己是谁。 |
| 2 |
memory-core插件 | 会话中通过memory
search/memoryget工具进行实时记忆搜索 |
| 3 | 神经图谱（nmem_context） | 联想回忆——12,393个神经元，40,532个突触。概念与概念相连。 |
| 4 | 夜间整合 | Gemini在你睡眠时将每日日志合并到CORE_MEMORY.md。无信息丢失。 |
| 5 | 连贯性监控器 | 草稿板遗忘检测——在漂移造成损害前触发重新锚定。33项测试全部通过。 |
核心洞察
记忆存在于文件中。模型只是阅读者。
当系统被完全清除并从零重建时，代理带着完整的连续性重新上线——因为身份文件幸存了下来。更换LLM，保留Vault。记忆持久存在。
设置
两种路径——任选其一：
路径1——自行操作（30–60分钟）
阅读SETUP_HUMAN.md。纯英文，无需技术背景。
路径2——让代理处理
将SETUP_AI.md粘贴到你的OpenClaw聊天中。它会询问8个问题并自行完成安装。
前提条件
- - 运行任意模型的OpenClaw
- Python 3.10+
- npm install -g mcporter
- NVIDIA开发者免费层API密钥（Kimi K2.5，131K上下文，免费）
- 用于夜间整合的Gemini API密钥（免费）
链接
- - 仓库： https://github.com/strangeadvancedmarketing/Adam
- 实时验证（353次会话）： https://strangeadvancedmarketing.github.io/Adam/showcase/ai-amnesia-solved.html
- 完整设置指南： https://github.com/strangeadvancedmarketing/Adam/blob/master/SETUP_HUMAN.md
