Alternatives
Products that do what How does JAX allocate memory on a TPU? An interactive C++ walkthrough does
- 1IW
A fun toy memory allocator (not thread safe, that's a future TODO). I also wanted to explain how I approached it, so I also wrote a tutorial blog post (~20 minute read) covering the code which you can find the link to in the README.
Nov 2025 · github.com
- 2MM
I've been working on implementing the compile-time approach to memory management described in this thesis (https://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-908.pdf) for some time now - some of the performance results look promising! (Although some less so...) I think it would be great to see this taken further and built into a more complete functional language.
2020 · github.com
- 3IB
We wanted to do something very challenging to prove to ourselves that we can do anything we put our mind to. The reasoning for why we chose to build a toy TPU specifically is fairly simple: - Building a chip for ML workloads seemed cool - There was no well-documented open source repo for an ML accelerator that performed both inference and training None of us have real professional experience in hardware design, which, in a way, made the TPU even more appealing since we weren't able to estimate exactly how difficult it would be. As we worked on the initial stages of this project, we…
2025 · tinytpu.com
- 4YA
Built this for my LLM workflows - needed searchable, persistent memory that wouldn't blow up storage costs. I also wanted to use it locally for my research. It's a content-addressed storage system with block-level deduplication (saves 30-40% on typical codebases). I have integrated the CLI tool into most of my workflows in Zed, Claude Code, and Cursor, and I provide the prompt I'm currently using in the repo. The project is in C++ and the build system is rough around the edges but is tested on macOS and Ubuntu 24.04.
2025 · github.com
- 5
- 6RG
Hey HN! I'm José, and I built Recall to solve a problem that was driving me crazy. The Problem: I use Claude for coding daily, but every conversation starts from scratch. I'd explain my architecture, coding standards, past decisions... then hit the context limit and lose everything. Next session? Start over. The Solution: Recall is an MCP (Model Context Protocol) server that gives Claude persistent memory using Redis + semantic search. Think of it as long-term memory that survives context limits and session restarts. How it works: - Claude stores important context as "memories" during…
Oct 2025 · npmjs.com
- 7JJ
Jan 2026 · ss.ekzhang.com
- 8IB
Hi HN! Korean high school senior here, about to start CS in college. I built a browser engine from scratch in C++ to understand how browsers work. First time using C++, 8 weeks of development, lots of debugging—but it works! Features: - HTML parsing with error correction - CSS cascade and inheritance - Block/inline layout engine - Async image loading + caching - Link navigation + history Hardest parts: - String parsing(html, css) - Rendering - Image Caching & Layout Reflowing What I learned (beyond code): - Systematic debugging is crucial - Ship with known bugs rather than chase…
Jan 2026 · github.com
- 9HE
I wrote a little LD_PRELOAD library that makes it easy to inspect and interact with a running program's glibc heap. It's fun to pause processes, free a bunch of their allocations, then resume them. Most of the time, the processes continue as though nothing happened, but sometimes they do interesting things :)
2025 · github.com
- 10FA
2021 · github.com
- 11TE
This project launches multiple independent programs into a single shared virtual address space, while still behaving like separate processes (independent binaries, globals, and lifetimes). When threadprocs share their address space, pointers are valid across them with no code changes for well-behaved Linux binaries. Unlike threads, each threadproc is a standalone and semi-isolated process. Unlike dlopen-based plugin systems, threadprocs run traditional executables with a `main()` function. Unlike POSIX processes, pointers remain valid across threadprocs because they share the same address…
Mar 2026 · github.com
- 12TA
Txeo is a lightweight and intuitive C++ wrapper for TensorFlow, designed to simplify TensorFlow C++ development while preserving high performance and flexibility. Built entirely with Modern C++, Txeo allows developers to use TensorFlow with the ease of a high-level API, eliminating the complexity of its low-level C++ interface.
2025 · github.com
- 13
An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents. - fellowgeek/mcp-memory
24d ago · github.com
- 14BA
Hi HN, Erik here. Today we launch Butter, an OpenAI-compatible API proxy that caches LLM generations and serves them deterministically on revisit. Since April, we’ve been working on this concept of “muscle memory,” or deterministic replay, for agent systems performing automations. You may recall our first post in May, launching a python package called Muscle Mem: https://news.ycombinator.com/item?id=43988381 Since then, the product has evolved entirely, now taking the form of an LLM Proxy. For a deep dive into this process, check out:…
Oct 2025 · docs.butter.dev
- 15TM
2017 · github.com
- 16TS
Hi everyone, I just released an open source load testing tool for LLMs: https://github.com/twerkmeister/tokenflood === What is it and what problems does it solve? === Tokenflood is a load testing tool for instruction-tuned LLMs hat can simulate arbitrary LLM loads in terms of prompt, prefix, and output lengths and requests per second. Instead of first collecting prompt data for different load types, you can configure the desired parameters for your load test and you are good to go. It also let's you assess the latency effects of potential prompt parameter changes before…
Nov 2025 · github.com
- 17AJ
2017 · github.com
- 18FE
2015 · github.com
- 19BA
Tired of AI coding tools that forget everything between sessions? Every time I open a new chat with Claude or fire up Copilot, I'm back to square one explaining my codebase structure. So I built something to fix this. It's called In Memoria. Its an MCP server that gives AI tools persistent memory. Instead of starting fresh every conversation, the AI remembers your coding patterns, architectural decisions, and all the context you've built up. The setup is dead simple: `npx in-memoria server` then connect your AI tool. No accounts, no data leaves your machine. Under the hood it's TypeScript +…
2025 · github.com
- 20PM
I built an MCP server that gives Claude Code long-term memory across sessions, backed by infrastructure you control. Every Claude Code session starts from zero, no memory of previous sessions. This server uses mem0ai as a library and exposes 11 MCP tools for storing, searching, and managing memories. Qdrant handles vector storage, Ollama runs embeddings locally (bge-m3), and Neo4j optionally builds a knowledge graph. Some engineering details HN might find interesting: - Zero-config auth: auto-reads Claude Code's OAT token from ~/.claude/.credentials.json, detects token type (OAT vs…
Feb 2026 · github.com
- 21MW
2017 · github.com
- 22IB
I wanted to share a project I have been working on over the past week. It is a simple local memory system that saves your sessions into Markdown files, which can be viewed later. I developed this after using Claude Mem. I really enjoyed working with it, but it was consuming a lot of RAM, and each Claude session was becoming a major resource hog. I also tried other plugins and MCP solutions, but ran into similar issues, either slow performance or concerns about data being sent elsewhere. Because privacy was a big thing for me, I decided to build my own solution that keeps all data local.
Feb 2026 · github.com
- 23WA
2025 · web-agent-memory.github.io
- 24SS
Hi HN! I've been building a project that handles high-value credentials in-process, and I wanted something more robust than just zeroing memory on drop. A comment on a recent Show HN[0] made me realize that awareness of lower-level memory protection techniques might not be as widespread as I thought. The idea here is to pull out all the tools in one crate, with a relatively simple API. * mlock/VirtualLock to prevent sensitive memory from being swapped (eg the KeePass dump) * Core dump exclusion using MADV_DONTDUMP on Linux & Android * mprotect to minimize exposure over time * Guard…
Mar 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →