I got tired of re-explaining myself to AI every single day.
So I built ThreadRecall, a local memory layer for all your AI tools.
Captures your conversations in realtime across Claude, ChatGPT, Codex, Gemini + Perplexity. Privately, on your Mac. No more starting from zero.
Waitlist is open → https://t.co/LlnkR01MBx
ChatGPT's new "Dreaming" memory rewrites what it knows about you in the background. OpenAI admits the memory summary doesn't show everything it's retained, and deleting a chat doesn't delete what was learned from it. 👇 see article below
I'm building ThreadRecall on the opposite bet: verbatim record of every AI conversation, local SQLite on your Mac. Nothing synthesized, nothing leaves the machine.
Here's what it does 👇 - Public beta now ava
I’m not an engineer.
I’m a creative director who started using AI tools the way a lot of people now use them: constantly, across different apps, for thinking as much as doing.
Claude for deeper reasoning. ChatGPT for quick drafts. Gemini or Perplexity for another angle. Codex when I’m working through software. Different tools, different strengths, often in the same day.
At first, that felt powerful. Then it started to feel strangely fragile.
Every good conversation lived in its own place. A product decision in Claude. A naming discussion in ChatGPT. A technical path in Codex. A research thread somewhere else. Each one made sense while I was inside it, but the moment I switched tools, the thinking stopped traveling with me.
I wasn’t losing files.
I was losing thinking.
That is the part that bothered me.
Not just the final answer. The path to the answer. The messy middle. The moment where a phrase finally clicked. The tradeoff I almost forgot. The reason I chose one direction over another. The small bit of context that made the next conversation better.
So I made ThreadRecall. Here is a demo to show it in action : Its not work related , but you'll get the idea. 😅 - ChatGPT context, recalled inside Claude.
A nice side effect, with this context retrieval : it can save tokens too.
ie When the relevant context is already captured and searchable, you don’t need to paste a giant recap into every new AI session. You can bring back the specific prior thread that matters.
That means less repeated setup, less bloated context, and more room for the actual work.
Join the waitlist - https://t.co/G1ex10giBt
Am working on this little project. because of frustration. making it free for all. https://t.co/LlnkR01MBx .... think this would be a nice combo.. join waitlist for now. fixing some bugss...
Prompt caching makes AI faster.
ThreadRecall makes AI remember better.
One optimizes the context you already have.
The other helps you bring back the context you actually need. Together, they make long-running agents a lot more practical.
@Neutrogena@xpander343 Hi I have used creams to manage my rashes, and none of them work, only Norwegian Formula Body Emulsion worked for me, and have been using it for 10 years. now I can't find anything that works, please bring it back!!
I now rely on ebay to buy the Japanese stock.