chenxiachan/thoughtdag
by Various
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
MCP
chenxiachan/thoughtdag
Added 9 Oct 2026
Overview
An open-source TypeScript tool that renders LLM conversations as an editable graph on an infinite canvas. Connections between nodes represent conversational context, allowing users to restructure how context flows between messages.
Best for
Best for
Developers building complex LLM workflows who need a visual, editable map of conversation context.
Use cases
- Visualize multi-branch LLM conversation trees
- Edit conversation context by rewiring node connections
- Map complex agent or prompt chains spatially
How to use
Install
npx thoughtdag why src/lib/api.ts # conversations about this fileTested with
Claude Code, Continue, ChatGPT
Notes
An open-source TypeScript tool that renders LLM conversations as an editable graph on an infinite canvas. Connections between nodes represent conversational context, allowing users to restructure how context flows between messages.
592 stars on GitHub. Last updated 2026-10-07. Licensed MIT.
Use cases
- Visualize multi-branch LLM conversation trees
- Edit conversation context by rewiring node connections
- Map complex agent or prompt chains spatially
Pros
- Open source with an active GitHub repository
- TypeScript codebase for type-safe customization
- Visual graph model makes context flow explicit
Cons
- Niche focus on LLM conversation graphs only
- Requires understanding of graph-based context representation
- Project maturity and documentation not detailed in available facts
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Open source with an active GitHub repository
- TypeScript codebase for type-safe customization
- Visual graph model makes context flow explicit
Cons
- Niche focus on LLM conversation graphs only
- Requires understanding of graph-based context representation
- Project maturity and documentation not detailed in available facts
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
upstash/context7
Various
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
vectorize-io/hindsight
Various
Hindsight: Agent Memory That Learns
topoteretes/cognee
Various
Memory platform for AI Agents in 6 lines of code
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.