Odin is a manually memory managed language. Beginners of such languages are often afraid of memory leaks, meaning that you forget to deallocate memory. The first remedy for this is to use the tracking allocator. It will warn you about memory you forgot to deallocate. Nifty! But you can also think along these lines: Can I simplify things a bit, so I don’t have to think about the deallocation? What you can do is to try to use the temporary allocator whenever possible.
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
GPU Poor LLM Arena - a Hugging Face Space by k-mktr
Compact LLM Battle Arena: Frugal AI Face-Off!
ChatGPT Memory and the Bitter Lesson
I reverse-engineered ChatGPT's memory system to understand what it stores, how it works (spoiler: not RAG!), and why OpenAI built it this way. Complete with prompts you can try yourself to explore your own ChatGPT memory.
OpenAI Developers on Twitter / X
Last week, we released a preview of memories in Codex.Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context.Now, Codex can help with what you’ve been working on without you restating context. pic.twitter.com/b3p8I5eXOy— OpenAI Developers (@OpenAIDevs) April 20, 2026
Memory in Agents: What, Why and How
LLM memory gives language models persistent context across sessions. Learn how it works, how it differs from RAG and context windows, and how to add LLM memory to your agents with Mem0.
I Benchmarked OpenAI Memory vs LangMem vs Letta (MemGPT) vs Mem0 for Long-Term Memory: Here’s How They Stacked Up
145 votes, 53 comments. Lately, I’ve been testing memory systems to handle long conversations in agent setups, optimizing for: Factual consistency…
Heaps do lie: debugging a memory leak in vLLM. | Mistral AI
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
Shlok Khemani on Twitter / X
Super interesting that eve doesn't ship with any long-term or cross-session memory (yet). The main context-management lever out of the box is conversation compaction. This is unlike OpenClaw and Hermes, each of which comes with a default opinionated memory implementation. https://t.co/DDIyc4rFtW— Shlok Khemani (@shloked) June 17, 2026
OpenMemory - AI Memory MCP Server for Coding Agents | Mem0
With OpenMemory, add persistent, project-aware memory to Cursor, Windsurf, and VS Code agents. Store preferences, patterns, and context that get retrieved automatically.
alphaXiv on Twitter / X
"Metis: Memory Foundation Model"Most AI agents still use memory as an external RAG-style module, so the model retrieves old text instead of actually remembering.This paper makes memory native to the Transformer. So past interactions are compressed into dynamic layer states… pic.twitter.com/YylDDXGX3G— alphaXiv (@askalphaxiv) July 31, 2026
Understanding memory management
Learn MemGPT memory management techniques for controlling LLM context windows with in-context and external storage.
Automerge 3.0
A new major version of Automerge, which cuts down memory usage by more than 10x while preserving backwards compatability.
Basic Memory
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
How to Fix OpenClaw's Memory Search with QMD | Jose Casanova
Upgrade OpenClaw's memory search from basic SQLite to QMD — a local hybrid search engine combining BM25, vector search, and LLM re-ranking for better AI memory.
What did the memory change? - Sensemaker
AI memory is entering the action loop. A list of saved facts does not show how those facts changed the result.