Show HN: Tiny project memory for coding agents
1 points, 0 comments on Hacker News
??????? #memory
30 headlines
Show HN: Local Context and Memory Stack
1 points, 0 comments on Hacker News
Brother's memory inspires Williams for World Cup opener
Ronwen Williams' brother Marvin, who died in a car crash in 2010, is a source of inspiration as the goalkeeper captains South Africa against Mexico in the opening match of the 2026 World Cup.
How memory tools can make AI models worse
New research suggests that AI memory systems can degrade model performance and encourage sycophantic tendencies.
We put the Bun Rust rewrite in production
At Prisma we've been working on a Compute offering to complement our hosted Postgres. We settled on Bun early in the process as we liked the experience we'd be able to provide thanks to Buns batteries-included approach. But then we started using Bun in anger, and we found many memory leaks in t...
Designing Memory for a Minimal Rust Coding Agent, Without a Vector Store
1 points, 0 comments on Hacker News
Hindsight Is the Fastest-Growing Open-Source AI Memory Project
2 points, 0 comments on Hacker News
Coding Agent Memory Benchmarks
Something I’m finding while testing SWE-context-bench for the agent memory layer I’m building: evaluating memory is harder than checking whether the agent solved the next task with fewer tokens. The setup: An agent solves a coding task. Later, it gets a related task that should benefit from the...
Show HN: Tenure – Traceable AI memory with configurable memory modes
3 points, 0 comments on Hacker News
Seagate: Is Storage Worth More Than Memory
Developing story — details emerging. Check the source link for the latest updates.
Cache Deep Dive IV — TLB, Huge Pages, and Memory-Level Parallelism
Earlier parts examined the performance characteristics of sequential and random access under single-threaded execution, and noted in passing the destructive effect of random access on the TLB. This part devotes full attention to the TLB: what it is, why a TLB miss is more severe than a cache mis...
How I Gave My AI Agent a Real Memory Without Touching Its Internals
As someone who runs multiple AI agents for day-to-day tasks, I kept hitting the same wall: every new conversation was a total memory wipe. I'd ask my agent about a project we discussed yesterday, and it had no idea what I was talking about. Frustrating.
Memory Safety Is a Matter of Life and Death
2 points, 0 comments on Hacker News
Efficient and accurate neural-field reconstruction using resistive memory
Nature, Published online: 10 June 2026; doi:10. 1038/s41586-026-10646-w A co-optimized AI hardware–software system using resistive-memory computing improves energy efficiency and parallelism for sparse signal reconstruction in imaging and three-dimensional vision applications.
Accelerating Transactional Execution via Processing-in-Memory
2 points, 0 comments on Hacker News
Why does tsgo use so much memory?
1 points, 0 comments on Hacker News
Replacing RAG with a cognitive memory stack in Elixir/OTP
1 points, 0 comments on Hacker News
The often-ignored system controlling your mood, memory, and focus
1 points, 0 comments on Hacker News
Show HN: AI agents join meetings with memory, calendar, and tasks
Meet with an AI agent you configure.
Trophic memory, deer, and a unique scientific object
2 points, 0 comments on Hacker News
Donwill on The Almanac of Rap, Hip-Hop Memory and the Lost Art of Context
The rapper/podcast host reflects on message boards, digital archiving and why the internet once invited listeners to dig deeper.
Micron and other memory makers are driving a ‘supercycle’ for this corner of the chip sector
Chip-equipment companies are getting unprecedented visibility into companies’ supply plans, a UBS analyst says.
Your GPU Is Probably Idle
A GPU holding memory isn't the same as a GPU doing work (an H100 can sit at 0% utilization with 20 GiB allocated), and most idle time comes from everything around the card, not the card itself. So feed it from the input pipeline, hand it big tensor-friendly shapes, fuse small kernels with torch....
Show HN: Lore – LLM proxy for coding agent context and memory management
4 points, 0 comments on Hacker News