Show HN: Graphicle, a Rust port of Graphify with memory for coding agents
KarLexAI
44 points
12 comments
October 14, 2026
Related Discussions
Found 5 related stories in 129.7ms across 9,516 title embeddings via pgvector HNSW
- Show HN: Minigraf – An embedded, bi-temporal graph database in Rust adityamukho · 34 pts · October 05, 2026 · 73% similar
- Show HN: Graphify C# – Compiler-accurate Find Usages for coding agents zachsaw · 28 pts · September 12, 2026 · 69% similar
- Show HN: I built a native app for coding agents with Rust and GPUI 0x142857 · 22 pts · August 16, 2026 · 64% similar
- Show HN: 49 IDE – 2D Canvas for Agents myradism · 18 pts · August 31, 2026 · 63% similar
- Show HN: XY – A Fast, composable, GPU-accelerated interactive plotting library apetuskey · 120 pts · July 28, 2026 · 63% similar
Discussion Highlights (5 comments)
pjm331
who out there is running evals of giving agents these kinds of tools and how are you doing it?
theLiminator
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.
blackspacx
How is the benchmarks of this tool? Did you programm the tool within help of AI?
dmos62
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.
cadamsdotcom
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.