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.

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.

In action

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

How ThoughtDAG differs

Many products use nodes and edges, but the graph does a different job in each category.

ThoughtDAG is a user-authored context graph: incoming paths and explicit references form the next request, while excluded work stays visible on the canvas.

🗺️ Export the shape of your thinking

The export keeps the nodes, wires and high-level structural counts. Different questions and different ways of exploring them leave visibly different maps.

Quick start

Desktop app

On macOS, install with Homebrew:

brew install --cask thoughtdag

Or 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.

Connect the Codex or Claude Code skill

Session Atlas discovers and opens your local sessions with no setup at all — and an open canvas keeps following its conversation on its own. To jump from a conversation straight to its canvas inside the agent:

• Claude Code: /thoughtdag
• Codex: $thoughtdag

Enable it in Session Atlas → Sources: the app installs one readable local command file, removable anytime.

Run from source

npm install
npm run server    # LLM proxy :3001
npm run dev       # → localhost:5173
# No .env? Connect any OpenAI-compatible endpoint inside the app

Environment variables, local models and connection details → docs/setup.md

Browser demo

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: Session Atlas, local session discovery, keyless web search, some direct-connection tools and the subscription bridge are desktop/local-only.

🧪 Research: Why editable context matters

Context Intervention Benchmark · Pilot v2

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

More capabilities

Full feature list (60+, grouped by area) → docs/features.md

Models, cost & privacy

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

Contributors

Contributions are welcome — start with CONTRIBUTING.md.

Supporters

With gratitude to @andreilaiter, ThoughtDAG's first supporter, and to everyone helping this independent open-source project grow.

---