Launched this week
Hermit
Leave ChatGPT while keeping everything it learned about you
162 followers
Leave ChatGPT while keeping everything it learned about you
162 followers
Switching LLMs means losing years of context. Anthropic's Import Memory official prompt extracts ~40 stored facts: about 2% of what's in your conversations. Hermit processes your full ChatGPT data export and generates one structured profile per ChatGPT project and recurring theme, with temporal awareness (ACTIVE vs PAST). Ready-to-paste files for Claude Memory, Claude Projects, Gemini Gems, or any LLM. Free analytics. One-shot pricing, not a subscription. Data deleted within 24h.
Free Options
Launch Team / Built With
Congrats on the launch and the great timing!👏 Just curious if you'll be creating something similar for other LLM platform exports, more specifically Perplexity in my case.
Hermit
@cinemachine Thanks! Perplexity is actually a great candidate: the conversation format is similar enough that the pipeline could adapt. Right now the input is ChatGPT only (it's where the biggest export files and the most urgent migration need are), but other providers are on the roadmap. Perplexity, Gemini, and Claude exports are the most requested so far. No timeline yet but it's coming.
Currently switching to Claude from others, let me check it out!
All the best for the launch!
Hermit
@krupali_trivedi Thank you! Perfect timing then. If you've already requested your ChatGPT export, you're good to go. If not, do it now (Settings > Data Controls > Export) - it takes 24-72h to arrive (maybe more right now with ppl hammering the Export button). Let me know how it goes!
@jkjakubowski Exporting was quite easy! now waiting for it to arrive!
Great timing, due to political reasons and so on I heard multiple people switching between models and this definitely helps. Also when you want to compare the results of another tool but need to provide plenty of context to be able to do so. All the best of luck!
Hermit
@viktorgems Thank you! Yess, the #QuitGPT wave is huge right now. Great point on the comparison use case: I hadn't thought of it that way but it makes a lot of sense. Instead of spending hours re-explaining your context to a second model, you just paste your Hermit profile and get a fair comparison from day one. Appreciate the kind words!
OpenAI: "here are 40 facts about yourself"
Hermit: "actually here are 95 patterns you didn't even know you had"
me: 😳 why does an AI know me better than my therapist
Hermit
@ilya_lee Haha the therapist comparison hits close to home, that's actually the analogy I use to explain it. Switching LLMs without your context is like changing therapist after 3 years and starting over from "so tell me about yourself."
Key Specifics are the part that surprises people most. From my own profile: "When the user asks about Tirith versus Beacons priorities, help him reason through the tension - Tirith is the dream, Beacons pays rent. Do not assume one is more important." Or: "When naming any new module or feature, always propose symbolic names drawn from Tolkien or Greek mythology: this is a non-negotiable design preference, not optional flavor."
Stuff I never explicitly told ChatGPT, but that Hermit extracted from 3 years of conversation patterns.
Glad it resonated! 🐚🦀