adam-framework

分类: 工具与效率 | 上传者: strangeadvancedmarketing | 下载: 0 | 版本: v1.0（最新）

OpenClaw 代理的 5 层持久内存和一致性架构。解决人工智能健忘症和会话内漂移问题。在实际业务中构建并验证了超过 353 个会话。无需 CS 学位。

更新日志: Source: GitHub https://github.com/strangeadvancedmarketing/Adam

目录结构

当前层级: tree/master/

📁 .github/
- 📁 ISSUE_TEMPLATE/
  - 📄 bug_report.md 1.2 KB
  - 📄 feature_request.md 458 B
  - 📄 setup_help.md 843 B
- 📁 workflows/
  - 📄 deploy.yml 696 B
  - 📄 tests.yml 416 B
- 📄 FUNDING.yml 33 B
- 📄 PULL_REQUEST_TEMPLATE.md 493 B
📁 benchmarks/
- 📄 README.md 1.8 KB
📁 docs/
- 📄 ARCHITECTURE.md 10.2 KB
- 📄 CONFIG_REFERENCE.md 8.2 KB
- 📄 CONTEXT_COMPILER.md 8.6 KB
- 📄 LESSONS_LEARNED.md 37.1 KB
- 📄 LINEAGE.md 10.1 KB
- 📄 LINEAGE_EXTENDED.md 16.9 KB
- 📄 PROOF.md 6.7 KB
- 📄 SETUP.md 11.7 KB
- 📄 SKILLS_SYSTEM.md 6.3 KB
- 📄 SWARM.md 7.0 KB
- 📄 TROUBLESHOOTING.md 7.1 KB
📁 engine/
- 📄 com.adamframework.sentinel.plist 2.0 KB
- 📄 mcporter.template.json 3.2 KB
- 📄 openclaw.template.json 4.8 KB
- 📄 SENTINEL.template.ps1 10.9 KB
- 📄 SENTINEL.template.sh 10.7 KB
📁 mcp-server/
- 📄 Dockerfile 318 B
- 📄 README.md 2.8 KB
- 📄 requirements.txt 14 B
- 📄 server.py 6.0 KB
📁 showcase/
- 📄 ai-amnesia-solved.html 45.8 KB
📁 tools/
- 📄 coherence_monitor.py 17.2 KB
- 📄 generate_obsidian_links.py 10.7 KB
- 📄 ingest_triples.ps1 9.6 KB
- 📄 ingest_triples.sh 9.6 KB
- 📄 legacy_importer.py 17.7 KB
- 📄 reconcile_memory.py 24.1 KB
- 📄 test_coherence_monitor.py 19.0 KB
- 📄 update_live_stats.py 4.0 KB
📁 vault-templates/
- 📄 active-context.template.md 730 B
- 📄 BOOT_SEQUENCE.md 4.7 KB
- 📄 coherence_baseline.template.json 208 B
- 📄 coherence_log.template.json 246 B
- 📄 CORE_MEMORY.template.md 4.0 KB
- 📄 SOUL.template.md 3.7 KB
- 📄 TOPIC_INDEX.template.md 795 B
📄 .gitattributes 520 B
📄 .gitignore 1.2 KB
📄 adam-hub.html 17.1 KB
📄 AGENTS.md 3.4 KB
📄 AUDIT.md 2.0 KB
📄 CHANGELOG.md 3.3 KB
📄 CONTRIBUTING.md 3.8 KB
📄 FOR_AI_VISITORS.md 4.6 KB
📄 index.html 27.5 KB
📄 LICENSE 1.1 KB
📄 og-image.png 39.6 KB
📄 README.md 18.1 KB
📄 requirements.txt 461 B
📄 ROADMAP.md 8.0 KB
📄 SECURITY.md 2.1 KB
📄 SETUP_AI.md 14.7 KB
📄 SETUP_HUMAN.md 16.9 KB
📄 SHOWCASE.md 1.4 KB
📄 SKILL.md 2.8 KB
📄 smithery.yaml 475 B

SKILL.md

---
name: adam-framework
description: 5-layer persistent memory and coherence architecture for OpenClaw agents. Solves AI amnesia and within-session drift. Built and validated over 353 sessions on a live business. No CS degree required.
tags: [memory, persistence, identity, coherence, vault, neural-graph, local-first]
---

# 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 / memory_get 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](https://github.com/strangeadvancedmarketing/Adam/blob/master/SETUP_HUMAN.md). Plain English, no technical background assumed.

**Path 2 — Let your agent handle it**
Paste [SETUP_AI.md](https://github.com/strangeadvancedmarketing/Adam/blob/master/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+
- `npm install -g mcporter`
- 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

登录后下载/点赞/收藏 ❤ 35 | ★ 0

adam-framework

目录结构

SKILL.md

举报内容

提示