strangeadvancedmarketing

strangeadvancedmarketing / Adam

Public

AI Amnesia solved. 5-layer persistent memory for local AI assistants. Built by a non-coder running a live business. 353 sessions. 8 months. One nuclear reset. Still running.

strangeadvancedmarketing.github.ioAdam agent-framework ai-agent ai-amnesia ai-memory autonomous-agent
15
3
100% credibility
Found Mar 06, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

The Adam Framework adds persistent memory layers and coherence monitoring to local AI assistants to prevent forgetting context between sessions and maintain reasoning quality during long chats.

How It Works

1
🔍 Discover Adam

You find the Adam Framework while searching for a way to stop your AI helper from forgetting everything between chats.

2
✅ Prepare your setup

Make sure your everyday AI chatting tool is already working on your computer.

3
Pick your setup path
👤
Do it yourself

Read friendly guides to create memory files and connect the pieces in about 30 minutes.

🤖
Let AI handle it

Hand the instructions to your AI, answer a few questions, and it builds the memory system.

4
📚 Add your history

Import chats from your old AI conversations so your helper instantly knows your projects and past decisions.

5
🌙 Enable overnight refresh

Turn on the gentle daily update that blends new chats into lasting memories while you sleep.

6
🛡️ Activate smart watch

Start the background guardian that keeps your AI focused and pulls it back if it starts to wander.

🎉 Perfect memory achieved

Your AI now remembers you, your work, and stays sharp across endless chats—no more repeating yourself.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 15 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Adam?

Adam is a Python framework that adds persistent memory to OpenClaw AI agents, fixing "AI amnesia" where assistants forget everything between sessions and drift during long chats. It layers vault injection for instant identity recall, neural graphs for associative memory, nightly log reconciliation via Gemini, and coherence monitoring to re-anchor drifting sessions. Users get an AI that wakes up knowing their projects, history, and priorities—import legacy chats from Claude or ChatGPT with simple CLI tools.

Why is it gaining traction?

Unlike one-off adam optimizer tweaks from adam paszke github or github adam bien's enterprise stacks, Adam delivers model-agnostic persistence: memory lives in plain files, surviving LLM swaps or rebuilds. The hook is production proof—353 sessions across 30 days on consumer hardware—plus dead-simple setup where your AI installs it itself. Devs dig the auto-sleep cycles that compound knowledge overnight without manual compaction.

Who should use this?

Solo devs or business owners running OpenClaw agents for daily workflows like lead tracking or project management. TurfTracker users re-explaining contractors every boot, or indie hackers seeding AI with ChatGPT history. Skip if you're not on OpenClaw or prefer cloud agents.

Verdict

Worth a 30-minute test if OpenClaw is your stack—docs and test coverage punch above 15 stars, but 1.0% credibility signals early days; fork and contribute for Linux ports. Solid for persistence pains, monitor for broader adoption.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.