ThoughtDAG – An editable context graph for LLM conversations
ThoughtDAG indexes local agent conversations across tools, finds the turns relevant to your work, and turns them into editable context graphs.
In plain words
ThoughtDAG is a tool that indexes agent conversations across multiple tools and creates editable context graphs for large language model interactions. It allows users to find relevant conversation turns and manually control which information enters each LLM request, making context decisions transparent and visible. The tool shows exactly what the model sees, what was removed, and maintains source links and token counts, giving users full control over their conversation context rather than relying on hidden memory selection.
written from the facts on this page · September 2026
From the sources
The prompt stayed the same. Polluted context changed the answer. No hidden memory selector. What the model sees, why, and what was removed stay visible in the graph. The interface shows what was said, not which history enters the next request. Ask from a selected passage, or turn a passage or figure into its own source-linked node. Provenance stays attached; context remains yours to wire. Preview source nodes, order, and token count. Context is no longer a hidden decision. The removed branch really leaves the request. The answer changes with the context. You decide what enters and leaves. The graph is the context protocol before generation. ThoughtDAG walks the incoming edges of a node,…from chenxiachan.github.io
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com