Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: ThoughtDAG – An editable context graph for LLM conversations

chenxiachan.github.io

Post reply on HN
Print view View original

71–80 of 82 posts

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#71

Post by fmoronzirfas »

chatchan wrote: post #12
agumonkey wrote: post #6

Earlier quoted context omitted.

have you seen other people or project on the same idea ? manipulation history and exploration space of LLM seems to be quite important

Yes, I have seen several adjacent approaches. Microsoft Huabu explores spatial interaction around research materials, while LLM Canvas and tldraw’s branching-chat experiments explore visual conversation trees. Many workflow canvases also use nodes and edges, but they usually represent execution pipelines. The specific interaction I am testing is more narrowly about context: an edge changes what the model receives, wh…

I vibe coded/sketched a similar idea for the obsidian canvas. https://github.com/ff6347/obsidian-canvas-context it is more a research artifact then a real product/tool.

I think I gave up at some point because it does not integrate with my agent workflow. I also try to keep my second brain free of AI generated text.

But it was a nice experiment. The biggest barrier is for me that it happens in a different space than the agents I run and it does not scratch an urgent itch. I think a bidirectional integration is crucial.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#72

Post by esperent »

chatchan wrote: post #35
esperent wrote: post #8

The basic idea here looks interesting and is easy to understand but what I'm not understanding is why it's a standalone app. Is this supposed to replace e.g. Claude desktop? Or can it plug in to other systems like Claude Code, Codex, Pi? I don't think I'd want to use it as a standalone app but I would certainly be interested in it as a plugin.

Thank you for your feedback! Just want to know. What would be the smallest useful integration for you: allowing the host tool to read the currently selected context, or bidirectional access so it can also create, branch, and prune nodes?

What would make this useful to me is integrating it into the tools I use. That's Pi, but I would say if you set it up for Claude Code or Codex that would get you more initial users.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#73

Post by chatchan »

frogperson wrote: post #67
mikeebener wrote: post #30

I looked at the repo and demo canvas. Nice work. Especially liked the 3 semantic zoom tiers and the weave/condense features. If you're enabling for less-technical users consider leading with weave and condense vs. edge deletion. Edge deletion is where the model is powerful but my Mom would get stuck there for instance. The idea that removing a wire changes what the model actually sees might not be obvious. Consider w…

There is no way to delete a highlight, I accidentally deleted the root node trying to remove a highlight, then the undo command wouldn't recall the root node . very cool ice over all, its earned a spot in my dock for now.

Thank you for your feedback!

There is a way to delete a highlight. On the node side panel, there is a folded highlight section; you can manage your highlights there. Also, on your canvas, top-right ... menu, you can manage your highlights as well.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#74

Post by chatchan »

esperent wrote: post #72
chatchan wrote: post #35

Earlier quoted context omitted.

Thank you for your feedback! Just want to know. What would be the smallest useful integration for you: allowing the host tool to read the currently selected context, or bidirectional access so it can also create, branch, and prune nodes?

What would make this useful to me is integrating it into the tools I use. That's Pi, but I would say if you set it up for Claude Code or Codex that would get you more initial users.

Yes. I agree. I've added a small section to the README in the Git repository to describe how it works alongside your coding agent.

ThoughtDAG has automatic folder backups as a JSON file. So you can ask your CLI to access it and get the context in your harness tools :)

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#77

Post by UltraSane »

chatchan wrote: post #70
UltraSane wrote: post #62

I've been working on something similar to this using Neo4j so you can control the context with a Cypher query because I really like Cypher. But this visualization is excellent.

Thanks! I'm not very familiar with Neo4j and Cypher yet. How do you control the context using Cypher? Do you manually write queries for each request, or do you select nodes through the interface and then automatically generate queries? I'm also curious about how the graph structure obtained from the query is ultimately transformed into an ordered model context.

I model the chat as a series of prompt and response nodes like

(prompt)-[:NEXT]->(response)

and can choose a given context by using a path query

MATCH p = (:prompt{id:})-[:NEXT*]->(:response{id:}) RETURN p

and extract the text from the nodes and format it as the API requires.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#78

Post by chatchan »

UltraSane wrote: post #77
chatchan wrote: post #70

Earlier quoted context omitted.

Thanks! I'm not very familiar with Neo4j and Cypher yet. How do you control the context using Cypher? Do you manually write queries for each request, or do you select nodes through the interface and then automatically generate queries? I'm also curious about how the graph structure obtained from the query is ultimately transformed into an ordered model context.

I model the chat as a series of prompt and response nodes like (prompt)-[:NEXT]->(response) and can choose a given context by using a path query MATCH p = (:prompt{id: })-[:NEXT*]->(:response{id: }) RETURN p and extract the text from the nodes and format it as the API requires.

Thanks, oh I see, Cypher acts as a context selector.

ThoughtDAG addresses the same issue but uses a visual approach: it searches for nodes first, then uses connections or references to determine which content enters the request. I'd love to see how it compares to writing Cypher directly, especially after conversations start branching and merging, if you get a chance to try it.

Post reply on HN