ThoughtDAG — Make LLM context visible and editable
The graph is the context."<br>data-zh-html="这不是一张上下文示意图。图本身，就是上下文。"<br>The graph is not a picture of context.<br>The graph is the context.
ThoughtDAG walks the incoming edges of a node, orders the relevant ancestors,<br>and builds the message sequence sent to the selected model. The structure stays<br>visible, editable, and inspectable.
Branch
Explore another interpretation without overwriting the path that led you<br>here.
Prune
Keep a useful detour on the canvas while excluding it from the next request.
Merge
Bring selected evidence and reasoning paths back together in one answer.
Inspect
Preview what the model will receive before generation. No hidden memory<br>selection.
Take it to the desktop
The same app in its own window, local engine bundled. No Node, no terminal.
v0.3.13
macOS Apple Silicon
Download .dmg<br>≈126MB
Intel Macs
Windows x64
Download installer<br>≈106MB
Linux x64
Download .AppImage<br>≈133MB
Install notes
macOS builds are signed and notarized by Apple: double-click and go. Windows builds are not signed yet; on the SmartScreen prompt choose "More info", then "Run anyway".
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.
CHAT HIDES CONTEXT.
THE GRAPH IS THE CONTEXT.
Linear conversation
Editable context graph
Same prompt · different context
AI conversation<br>87 messages
Compare three research paths.
Start with the first. Its advantage is…
What if the core hypothesis fails?
Consider another explanation…
Also, what should I eat tonight?
There is a new restaurant nearby.
The history is here. Which parts enter the next request?
research-paper.pdfp.7
Results
The effect appears only in the experimental condition.
Selected from the page
Clipped passageresearch-paper.pdf · p.7
The effect appears only in the experimental condition
Source linked · not wired yet
Asked from sourceresearch-paper.pdf · p.7
What does this evidence actually mean?
The source is in context
Unrelated branchdetour
What should I eat tonight?
This history should not enter the research summary.
Still connected
Polluted summary<br>3 sources
Research summary… also, consider hot pot for dinner.
The prompt stayed the same. Polluted context changed the answer.
Includes unrelated branch
Will send1,284 tokens
Preview what the model will receive
Incoming ancestors:
Research question<br>Evidence A<br>Dinner detour
After deleting the orange edge: −47 tokens
Context diff−47 tok
The dinner detour left context
Same prompt · regenerate
Same promptask again
Give me a bullet-point summary
The words are identical. Only one edge changed.
Reproducible context
Clean answer<br>2 sources
One: record the database version. Two: use independent reviewers. Three:<br>resolve conflicts with a third reviewer.
The unrelated dinner suggestion is gone.
Answer updated in place
One ruleThoughtDAG
Wires are context.
No hidden memory selector. What the model sees, why, and what was removed<br>stay visible in the graph.
Visible<br>Editable<br>Inspectable
01 · The problem<br>Context is still invisible."<br>data-zh-html="聊天越聊越长，上下文反而越来越模糊。"<br>Chat history is long. Context is still invisible.
The interface shows what was said, not which history enters the next request.
02 · Externalize<br>Clip what matters."<br>data-zh-html="从原文直接追问，<br>也把重要的摘到画布。"<br>Ask from the source. Clip what matters.
Ask from a selected passage, or turn a passage or figure into its own<br>source-linked node. Provenance stays attached; context remains yours to wire.
03 · Inspect<br>inspect what the model will read."<br>data-zh-html="生成之前，先看清模型的上下文。"<br>Before sending, inspect what the model will read.
Preview source nodes, order, and token count. Context is no longer a hidden<br>decision.
04 · Edit<br>Ask the same question again."<br>data-zh-html="剪掉一条线。<br>同一个问题，<br>再问一次。"<br>Delete one edge. Ask the same question again.
The removed branch really leaves the request. The answer changes with the<br>context.
05 · The protocol<br>ThoughtDAG edits context."<br>data-zh-html="很多画布只是在整理信息。ThoughtDAG 让你直接编辑模型的上下文。"<br>Most canvases organize information. ThoughtDAG edits context.
You decide what enters and leaves. The graph is the context protocol before<br>generation.
1 / 5<br>Invisible context