chenxiachan/thoughtdag
An infinite-canvas note-taking and LLM conversation tool that visualizes exchanges as a branching thought graph.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
ThoughtDAG is a local-first desktop and CLI application that turns LLM conversations into an editable directed acyclic graph on an infinite canvas. Each exchange becomes a node, and wires between nodes define the context the model sees on the next turn. It supports multiple LLM backends (Ollama, DeepSeek harness, MCP), provides a local index for retrieving past sessions, and includes a Jev decision layer for ranking relevant excerpts before they are added to a prompt.
Frequently asked
- What is chenxiachan/thoughtdag?
- An infinite-canvas note-taking and LLM conversation tool that visualizes exchanges as a branching thought graph.
- Is thoughtdag open source?
- Yes — chenxiachan/thoughtdag is open source, released under the MIT license.
- What language is thoughtdag written in?
- chenxiachan/thoughtdag is primarily written in TypeScript.
- How popular is thoughtdag?
- chenxiachan/thoughtdag has 503 stars on GitHub.
- Where can I find thoughtdag?
- chenxiachan/thoughtdag is on GitHub at https://github.com/chenxiachan/thoughtdag.