Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- How is the benchmarks of this tool? Did you programm the tool within help of AI?by blackspacx
- who out there is running evals of giving agents these kinds of tools and how are you doing it?by pjm331
- Does this have the same number of nodes limit as graphify?by chaostheory
- I'm sure it works great for its creator - but, without benchmarks of quality vs. an agent that can grep, it's hard to know if this project adds value.by cadamsdotcom
- The memory invalidation based on tying memories to pieces of code (e.g. functions) is the big thing here, I think, though I see why it wouldn't be front and center.
I've always found memory systems icky, because it's difficult to tell whether a memory is still valid. Also, discoverability is always a concern (when is a memory relevant). This being both a code-graph and a memory system (seemingly unrelated things), actually addresses this in a novel way.
by dmos62 - Has anyone actually gotten good results out of this?
For the evals I've run (albeit, not super scientific), these memory systems did worse than the raw harness given ripgrep.
by theLiminator