ThoughtDAG

Your thinking deserves a map. An infinite canvas where LLM conversations grow into an editable thought graph.

▶ Try it live

no install, no signup; the example canvas needs no key

中文 · Quick start · More capabilities · Models · Cost & privacy

Hero demo, recorded from the live app: selecting a passage in the PDF reader and asking about it; deleting a noise edge and regenerating a clean answer; zooming out through three semantic tiers to the map; opening the backup control center and exporting a real file

The one rule

Wires are the context. What the model sees is exactly what wires into the node. Editing the graph edits the model's memory.

In action

One principle behind every gesture: the human in the loop, the model on the wires. No autonomous agent redraws your graph.

Illustration: the research chain wired to a summary node, with the edge to a dinner node cut into a red dashed line

✂️ Delete one edge, get a different answer

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.

📖 Read a paper into a map

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.

Illustration: a passage selected on the original page, a purple ask bubble beside it, the paragraph tagged p.3

Illustration: three small highlighted cards converge through wires into one synthesis card, above a small timeline with cognitive badges

💎 Thinking condenses in your hands

Merge nodes into one higher conclusion; weave highlights into a summary. The graph folds inward instead of sprawling. The human refines in the loop.

🖍️ The passages you marked, woven into cited prose

Highlights are your judgment, not the model's. Check any subset and weave one passage where every sentence traces back.

Illustration: a highlighted sentence in a card woven into a cited passage below, with reference numbers

Illustration: three takeaway plaques with ruled-out, decided and pivoted badges, linked by dashed lines

🗺️ Zoom out: thinking becomes a map

Full cards, takeaway plaques, an icon skeleton: three semantic tiers, every step badged ✕ ⚖ ↩ ?. The detours are part of the map.

Quick start

# Online: app.thoughtdag.workers.dev (example canvas needs no key)
# Local:
npm install
npm run server    # LLM proxy :3001
npm run dev       # → localhost:5173
# No .env? Connect any OpenAI-compatible endpoint inside the app

The first launch opens a seeded example canvas: four chapters around one everyday question (why saved articles stay unread), including a reading loop with a real embedded PDF. Environment variables, free keys and configuration details → docs/setup.md

More capabilities

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
🧪 Paradigms	Human-machine workflows saved as files; change the input, replay the experiment
🔌 Any model	Per-node pins that follow the line; image requests reroute to vision models automatically
🔒 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

Supported models

Zhipu · Qwen · OpenAI · Anthropic · Google · DeepSeek · Kimi · OpenRouter · Ollama, or any OpenAI-compatible endpoint. Requests with images reroute to vision models automatically. Environment variables and default models → docs/setup.md

Cost & privacy

The free model tier covers every feature; a local Ollama runs fully offline
On the hosted demo, model traffic runs browser-direct: 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

The graph is acyclic. You are the loop.