cd /news/artificial-intelligence/i-made-thoughtdag-llm-as-an-editable… · home topics artificial-intelligence article
[ARTICLE · art-67824] src=github.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

I made ThoughtDAG – LLM as an editable graph, wires are the context

ThoughtDAG, an open-source tool that turns LLM conversations into editable thought graphs, launched with no install or signup required. The project, hosted on GitHub, lets users wire nodes to control exactly what the model sees, with features like read-only sharing, staleness tracking, and local-first backups. It supports models from Zhipu, Qwen, OpenAI, Anthropic, Google, DeepSeek, Kimi, OpenRouter, and Ollama, with a free tier covering all features.

read2 min views2 publishedJul 22, 2026
I made ThoughtDAG – LLM as an editable graph, wires are the context
Image: source

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

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

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

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

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. |

| 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. |

| Merge nodes into one higher conclusion; weave highlights into a summary. The graph folds inward instead of sprawling. |

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

| Full cards, takeaway plaques, an icon skeleton: three semantic tiers, every step badged ✕ ⚖ ↩ ?. |

npm install
npm run server    # LLM proxy :3001
npm run dev       # → localhost:5173

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

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

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

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

── more in #artificial-intelligence 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/i-made-thoughtdag-ll…] indexed:0 read:2min 2026-07-22 ·