“I want ChatGPT with infinite local memory” - Here’s how
Related videos
Claude Code can now make videos, here’s how
David Ondrej
30.7k views
Create Anything with Nano Banana Pro, Here’s How
David Ondrej
26.3k views
Fine-tune your own LLM in 13 minutes, here’s how
David Ondrej
74.4k views
How to create any n8n workflow using ChatGPT
David Ondrej
78.6k views
Build Anything with Gemini 2.5 Pro, Here’s How
David Ondrej
63.2k views
Start Vibe Coding Like a Pro, Here’s How
David Ondrej
43.0k views
Build anything with n8n, here’s how
David Ondrej
49.8k views
Build Anything with MCP Agents, Here’s How
David Ondrej
232.4k views
Build Anything with Claude 3.7, Here’s How
David Ondrej
88.2k views
Build Anything with Grok 3, Here's How
David Ondrej
110.1k views
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
Claude Code can now make videos, here’s how
David Ondrej
30.7k views
Create Anything with Nano Banana Pro, Here’s How
David Ondrej
26.3k views
Fine-tune your own LLM in 13 minutes, here’s how
David Ondrej
74.4k views
How to create any n8n workflow using ChatGPT
David Ondrej
78.6k views
Build Anything with Gemini 2.5 Pro, Here’s How
David Ondrej
63.2k views
Start Vibe Coding Like a Pro, Here’s How
David Ondrej
43.0k views
Build anything with n8n, here’s how
David Ondrej
49.8k views
Build Anything with MCP Agents, Here’s How
David Ondrej
232.4k views
Build Anything with Claude 3.7, Here’s How
David Ondrej
88.2k views
Build Anything with Grok 3, Here's How
David Ondrej
110.1k views
Top Comments (10)
If you are sending data to OpenAI it is not private. Summarising the private information, does not remove the private information, just makes it concise.
I've been a software engineer close to 20 years now - and with the age of AI tools - you are my goto for the latest and greatest! THANK YOU!
bro I was thinking about it this instant and your video shows in my feed. the algo broke my brain
Not sure if anyone else noticed, but that extra STDIO server process you launched you didn’t need at all. Claude launches a process itself and then passes JSONRPC commands back and forth within the STDIO session it creates with its own process. The spare one you launched would have been totally idle. But cool and concise breakdown of this idea, thanks for posting this.
Mem Agent looks awesome as a lightweight way to give LLMs sticky long-term memory across tools. I’ve also been following Archon, which takes more of an “AI OS for coding” approach — not just memory, but also RAG over docs, project/task management, and a full MCP server with a human-facing UI. Feels like the two could be really complementary: Mem Agent keeping assistants personally consistent, Archon organizing the bigger project context. Would be cool to see them integrate down the road.
If we are going to filter sensitive memory, why even add that memory to mem-agent? Wouldn’t safest approach be to not add and context that you don’t want exposed? Or am I missing something? I have been using mem0 locally so curious how it compares.
This dudes always on point with these tutorials.
🤖Learn how to make money with an AI business: https://www.skool.com/new-society 🔥Try Vectal for free: https://www.vectal.ai/
26 seconds into the video and I’ve installed the repo. 🎉 So grateful
yes, this is so cool! excellent tutorial!! robust local memory will be a huge unlock for many use cases.
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
If you are sending data to OpenAI it is not private. Summarising the private information, does not remove the private information, just makes it concise.
I've been a software engineer close to 20 years now - and with the age of AI tools - you are my goto for the latest and greatest! THANK YOU!
bro I was thinking about it this instant and your video shows in my feed. the algo broke my brain
Not sure if anyone else noticed, but that extra STDIO server process you launched you didn’t need at all. Claude launches a process itself and then passes JSONRPC commands back and forth within the STDIO session it creates with its own process. The spare one you launched would have been totally idle. But cool and concise breakdown of this idea, thanks for posting this.
Mem Agent looks awesome as a lightweight way to give LLMs sticky long-term memory across tools. I’ve also been following Archon, which takes more of an “AI OS for coding” approach — not just memory, but also RAG over docs, project/task management, and a full MCP server with a human-facing UI. Feels like the two could be really complementary: Mem Agent keeping assistants personally consistent, Archon organizing the bigger project context. Would be cool to see them integrate down the road.
If we are going to filter sensitive memory, why even add that memory to mem-agent? Wouldn’t safest approach be to not add and context that you don’t want exposed? Or am I missing something? I have been using mem0 locally so curious how it compares.
This dudes always on point with these tutorials.
🤖Learn how to make money with an AI business: https://www.skool.com/new-society 🔥Try Vectal for free: https://www.vectal.ai/
26 seconds into the video and I’ve installed the repo. 🎉 So grateful
yes, this is so cool! excellent tutorial!! robust local memory will be a huge unlock for many use cases.