cd /news/ai-tools/thoughtdag-testing-explicit-graph-co… · home topics ai-tools article
[ARTICLE · art-98768] src=discuss.huggingface.co ↗ pub= topic=ai-tools verified=true sentiment=· neutral

ThoughtDAG: testing explicit graph context control for local LLMs

ThoughtDAG, an open-source, local-first workspace by developer chenxiachan, lets users control LLM context by wiring nodes so only upstream nodes are serialized into the next model request. The author is running a context-control benchmark pilot with three perturbation families and invites feedback from local model users. The tool supports Ollama and OpenAI-compatible endpoints, storing data locally.

read1 min views1 publishedAug 16, 2026

Hi everyone, I am the author of ThoughtDAG, an open-source, local-first workspace built around one testable rule: wires are the context.

Each question-and-answer exchange is a node. When a user asks from a node, only its wired upstream nodes are serialized into the next model request. If an edge is removed and the same prompt is regenerated, that branch disappears from the actual input rather than only from the visualization.

I built it for research workflows where one question branches into several hypotheses, source documents, extracted passages, and counterexamples. The user can keep exploratory branches visible while deciding which evidence should continue into the next inference.

I am currently running a small context-control benchmark pilot with three perturbation families:

The required comparison uses the same fixed model and settings:

I would especially value feedback from people running local models:

ThoughtDAG supports Ollama for fully local inference and arbitrary OpenAI-compatible endpoints. The desktop app stores canvases, documents, and keys locally.

Project source and setup: GitHub - chenxiachan/thoughtdag: Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context. · GitHub

This is an early prototype and the benchmark is still running. I am more interested in failure cases and critiques of the interaction model than in general project promotion.

── more in #ai-tools 4 stories · sorted by recency
── more on @thoughtdag 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/thoughtdag-testing-e…] indexed:0 read:1min 2026-08-16 ·