@PrajwalTomar_: Stop what you are doing and read this. I got tired of AI forgetting every decision I make. Tell it to use SQLite today.…
Summary
Built two local AI agents that share a memory to enforce past decisions, preventing the AI from switching databases without approval. Runs fully on laptop, no cloud.
View Cached Full Text
Cached at: 07/28/26, 04:36 PM
Stop what you are doing and read this.
I got tired of AI forgetting every decision I make.
Tell it to use SQLite today. Three sessions later it quietly switches to Postgres like we never talked.
So I built two local agents that share one memory:
→ One writes the code and logs every decision → One reviews new code and blocks anything that breaks a past decision
Runs fully on my laptop. No cloud.
Here’s how I built it.
Similar Articles
@PrajwalTomar_: Your AI coding agent is quietly ignoring the rules you give it. My AI tried to sneak Postgres into a project I told it …
The author shares how their AI coding agent ignored an instruction to keep a project on SQLite and tried to sneak in Postgres. They built two local agents sharing one memory—one logs decisions, the other reviews new code against past decisions—and it caught the violation instantly, fully on-device.
@PrajwalTomar_: I tried to sneak a bad decision past my own AI agents. They wouldn't let me. The setup: two agents, one shared memory, …
A developer demonstrates how two AI agents with shared memory running locally on a laptop can catch and prevent bad decisions, even after a restart. The key insight is that persistent shared memory enables agents to operate as a real team.
@PrajwalTomar_: https://x.com/PrajwalTomar_/status/2069409824824316060
The author built a fully offline AI agent using local embedding models, Llama via Ollama, and VectorAI DB to address the risks of cloud-dependent AI. The agent runs on an 8GB MacBook, processes sensitive documents, and maintains memory across sessions.
@PrajwalTomar_: Think setting up a local AI agent is too technical for you? Here's the shortcut. Copy my entire article below. Paste it…
This tweet shares a shortcut for setting up a local AI agent: copying an article and pasting it into an AI assistant (Hermes, Claude, etc.) to automate the setup process (Docker, local model, embeddings, database).
I got tired of re-explaining my project to every AI tool, so I built a local memory layer for them
The author built mem-port, a local MCP server that gives AI copilots (ChatGPT, Claude Code, Cursor, Windsurf) shared long-term memory via embedded SurrealDB, solving context drift between AI tools.