Show HN: Open-source extension to fork Claude chats preserving context and files

Show HN: Open-source extension to fork Claude chats preserving context and files(chromewebstore.google.com)

4 points by ryanwaldorf 1 year ago | 1 comment

I built a Chrome extension that lets you fork Claude conversations to avoid token limits while preserving full context and files. It's completely free and open source.

Key features: - Adds "Create new Chat from Here" button to Claude responses - Preserves all context including user-provided and Claude-generated files - Works locally in your browser - no data leaves your machine - Formats conversation history for seamless continuation in new chats

Common use case: When Claude suggests multiple tasks/approaches, you can fork the conversation at that point and explore each path separately without hitting token limits. Claude maintains full context of the original discussion.

The extension helps you navigate Claude's token limitations more efficiently - instead of having Claude reprocess the entire conversation history with each response, you can create focused branches for specific subtasks.

GitHub: https://github.com/ryanwith/claude-continue-from-here

Would love feedback from the HN community on improving this further.

ryanwaldorf 1 year ago |

What motivated this: I kept hitting token limits when working with Claude on tasks with many parts. For instance, Claude would recommend three different areas of code to work on, but by the time I started on the second area, I'd get token limit warnings. This happened because Claude needs to process the entire conversation history with each response, even though the discussion of the first area is often unrelated to the second.

This extension lets you fork the conversation at any point, preserving all context and files up to that point while starting fresh with the token count. You can simply copy and paste it into a new chat or (download it as a file to attach) and continue your chat. Your conversation continues from the forked point as if it were the same conversation.