Deleting an edge actually removes that branch from the next model request, which is the whole point here. The preview of ancestors, order, and token count makes context pollution concrete instead of hand-wavy. If branches merge, I'd want to inspect the exact final message sequence.
ThoughtDAG
Make LLM context visible and editable
7 ratings3.92
Saves136
CategoryProductivity
PlatformWeb
PricingFree
ThoughtDAG indexes local agent conversations across tools, creating editable context graphs that make the context for large language model interactions visible, inspectable, and directly modifiable. It helps users manage and curate the context that LLMs see when generating responses, improving relevance and accuracy.
Ratings & Reviews
Write a reviewInformation
CategoryProductivity
PlatformsWeb
PricingFree
AccountNot confirmed
ListedAugust 2026
WebVisit
Report a problem
Website checks
Mobile PageSpeed
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 25, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 94 out of 100, Good
- Accessibility
- 95 out of 100, Good
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Around the Web
Show HN136 source points · 0 comments