cd /news/ai-tools/show-hn-thoughtdag-an-editable-conte… · home topics ai-tools article
[ARTICLE · art-97645] src=chenxiachan.github.io ↗ pub= topic=ai-tools verified=true sentiment=· neutral

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

ThoughtDAG, an editable context graph for LLM conversations, launched as a Show HN project with a web demo and desktop app, allowing users to branch, edit, and inspect the context sent to language models. The desktop app includes keyless web search and local storage, with version v0.3.13 available on GitHub Releases.

read1 min views1 publishedAug 15, 2026
Show HN: ThoughtDAG – An editable context graph for LLM conversations
Image: source

Branch

Explore another interpretation without overwriting the path that led you here.

ThoughtDAG turns every question-and-answer exchange into a node, and every connection into context. Remove one edge, ask the same question again, and that branch is gone from the request.

The web demo is a feature subset for a quick look — the example canvas needs no key. The desktop app is the full instrument: keyless web search, every connection tool, and your canvases living on your own machine.

ThoughtDAG walks the incoming edges of a node, orders the relevant ancestors, and builds the message sequence sent to the selected model. The structure stays visible, editable, and inspectable.

Explore another interpretation without overwriting the path that led you here.

Keep a useful detour on the canvas while excluding it from the next request.

Bring selected evidence and reasoning paths back together in one answer.

Preview what the model will receive before generation. No hidden memory selection.

The same app in its own window, local engine bundled. No Node, no terminal.

v0.3.13 All versions and history live on GitHub Releases. The desktop and web apps are the same app; your canvases stay on your device either way.

The history is here. Which parts enter the next request?

This history should not enter the research summary.

Still connectedThe prompt stayed the same. Polluted context changed the answer.

Includes unrelated branchIncoming ancestors:

Research question Evidence A Dinner detourAfter deleting the orange edge: −47 tokens

The words are identical. Only one edge changed.

Reproducible contextThe unrelated dinner suggestion is gone.

Answer updated in placeNo hidden memory selector. What the model sees, why, and what was removed stay visible in the graph.

Visible Editable Inspectable

── more in #ai-tools 4 stories · sorted by recency
── more on @thoughtdag 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-thoughtdag-a…] indexed:0 read:1min 2026-08-15 ·