Your thinking deserves a map. An infinite canvas where LLM conversations grow into an editable thought graph.
中文 · Quick start · How it differs · Research · Models & privacy
Wires are the context. What the model sees is exactly what wires into the node. Editing the graph edits the model's memory.
Many tools put conversations on a canvas. In ThoughtDAG, a wire is not decoration or an execution route. It determines what the model sees next.
One principle behind every gesture: the human in the loop, the model on the wires. No autonomous agent redraws your graph.
 |
The model sees only what wires in. Delete the noise edge, ask again, and the same prompt returns a clean answer. Reproduce it in chapter ③ of the example canvas. |
|
Select a passage, ask right there. The answer lands on the canvas with its page number, and the p.N chip jumps back to the page. Finish the paper, and the map is drawn. |
 |
 |
Merge nodes into a higher conclusion; weave highlights into cited prose. Zoom through full cards, takeaway plaques and an icon skeleton. Then export the current structure as a light or dark Thought Map. |
Many products use nodes and edges, but the graph does a different job in each category.
| Product category | How it differs from ThoughtDAG |
|---|---|
| Linear chat | Context follows one chronological thread; ThoughtDAG selects and merges visible paths. |
| Mind maps and whiteboards | Edges organize ideas for people; ThoughtDAG edges also change model input. |
| Branching chat canvases | They usually follow one inherited branch; ThoughtDAG can merge or prune several paths. |
| Workflow and agent canvases | Edges run tasks and data; ThoughtDAG edges control conversational context. |
| RAG and automatic memory | The system retrieves context automatically; ThoughtDAG makes the selection visible and editable. |
ThoughtDAG is a user-authored context graph: incoming paths and explicit references form the next request, while excluded work stays visible on the canvas.
The export keeps the nodes, wires and high-level structural counts. Different questions and different ways of exploring them leave visibly different maps.
On macOS, install with Homebrew:
brew install --cask thoughtdagOr use the download page, which detects your platform and gives you the right installer; Releases keeps every build. macOS builds are signed and notarized. Windows builds are not signed yet and may show a SmartScreen warning.
npm install
npm run server # LLM proxy :3001
npm run dev # → localhost:5173
# No .env? Connect any OpenAI-compatible endpoint inside the appEnvironment variables, local models and connection details → docs/setup.md
Want a ten-second look before installing anything? The hosted demo runs in the browser, and the example canvas needs no key. It is a feature subset: keyless web search, some direct-connection tools and the subscription bridge are desktop/local-only.
9 models · 1,485 test runs · $0 in free tiers · answers scored by exact match
Context does not only fade as conversations grow longer. A wrong statement flows into the replies that come after it and undermines the truthfulness of every later conclusion. Our benchmark verified this across nine language models and found the effect to be widespread: deleting the message that introduced the error is often not enough, because the follow-up replies still carry it. Restoring correct answers required cleaning up the affected passage as a whole, or letting the model rewrite it. In one model whose step-by-step thinking we could switch on and off, the minimal cleanup only worked while thinking was on. Managing context, not just accumulating it, decides what a model gets right.
The full report explains the method, the numbers and their statistics, and what this does and does not establish. It does not rank models and does not explain their inner workings; it tests one observable claim: changing what a model sees changes what it answers next.
📖 Read the first case study · 📊 Methodology and results · 🗳️ Suggest the next model · 🧪 Contribute a run or case
| Capability | What it does |
|---|---|
| 📤 Read-only share | One link carries the whole graph: no account, no server storage |
| 🧭 Staleness & replay | Upstream edits mark the answers they invalidate; replay in dependency order, token estimate first |
| ✂️ Clipping | Select a passage or drag a rectangle in the reader; it becomes canvas material with page provenance |
| 🔌 Any model | Per-node pins that follow the line; text-only models read images through their companion text |
| 🔒 Local-first | Automatic folder backup writes real files; point it at a synced folder for cross-device |
Full feature list (60+, grouped by area) → docs/features.md
Automatic folder backup keeps the canvas as a live .thoughtdag.json file in your project; Markdown export turns any context chain or selection into a plain .md. Coding agents can read either without a plugin, API or server.
Connect a local Ollama or any OpenAI-compatible endpoint. Built-in presets, subscription connections and environment variables are documented in setup.
- The free model tier covers every feature; a local Ollama runs fully offline
- In the desktop app everything lives on your machine: canvases, keys, documents; on the web demo, model traffic runs browser-direct and keys never touch the server
- PDFs never leave your machine; only extracted text travels when you ask
- The backup format stays backward compatible; Markdown export is the permanent escape hatch
With gratitude to @andreilaiter, ThoughtDAG's first supporter, and to everyone helping this independent open-source project grow.
