Graphlink replaces the linear chat window with a canvas of connected nodes. Instead of forcing every idea into one timeline, you branch — and each branch follows its own line of inquiry, with its own model and its own context. It runs entirely on your machine. Local models through Ollama or llama.cpp, or hosted APIs (OpenAI-compatible, Anthropic Claude, Google Gemini) if you prefer. Your conversations, notes, and layouts stay in a local database. Shown in this video: • Branching canvas — parallel paths in one view • Document View — read any branch as a formatted document • The Builder — give it a goal, it plans a checklist and constructs it on the canvas one supervised step at a time, under hard step/token/time limits • Canvas controls — themes, grid, connection routing, font size • Command palette — everything reachable from the keyboard Also in the app: specialist nodes for web research, Python execution, and repo-aware editing; a local knowledge base you can search; charts from any node; and undo that can reverse an entire agent run in one action. Free and open source (MIT): https://github.com/dovvnloading/Graphlink Chapters 0:00 Intro 0:05 The branching canvas 0:16 Document View 0:27 The Builder — planning a run 0:38 The Builder — building on the canvas 0:52 Canvas controls and command palette 1:08 Wrap Music: Redline (2026 Remaster)
The information provided is not trading advice. kdj.com does not assume any responsibility for any investments made based on the information provided in this article. Cryptocurrencies are highly volatile and it is highly recommended that you invest with caution after thorough research!
If you believe that the content used on this website infringes your copyright, please contact us immediately (info@kdj.com) and we will delete it promptly.