Transfercc
Contextual migration from ChatGPT history to Claude
What it does
Transfercc lets you move your ChatGPT conversations into Claude without losing context. Browse your full chat history in a clean UI, search everything, keep projects and smart groups intact, and export conversations as Claude-ready Markdown. Runs locally, open-source, privacy-first. Built for power users who don’t want to start over.
Does the same job
all alternatives →
Claude Import MemoryMar 2026 · claude.com · ▲725Switch from ChatGPT to Claude with import memory feature
Move your chats from ChatGPT to ClaudeApr 2026 · chatgpt2claude.com · ▲10Secure, private and easy chat and context migration tool
- GYGet your entire ChatGPT history in Markdown files2023 · github.com · ▲295
This is just a small thing I coded to help me see my entire convo history in beautiful markdown, in Obsidian (my note-taking app). [Link to Github repo](https://github.com/mohamed-chs/chatgpt-history-export-to-md). The Python script helps you to convert conversations extracted from ChatGPT (ZIP export all your data, sent by Openai) into neatly formatted Markdown files. Also adds YAML metadata headers and includes Code interpreter (Advanced data analysis) intput / output code. Feel free to fork the repo and implement your own improvements, I feel like there's alot…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
