How we built Engrava: from cognitive-architecture research to a production library
Deterministic consolidation, a typed graph in SQLite, and an honest look at what agent-memory benchmarks can and can't measure. You're building an age…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
Why Your Team's AI Assistant Acts Like It's the First Day on the Job, Every Single Time
Anyone who has used AI tools for a while has probably run into this annoyance. You ask it to write a weekly report in the morning and it doesn't know …
Mem0 vs TurboMem: which memory layer actually fits your TypeScript agent
Mem0 is the name everyone hears first. If your agent runs in TypeScript, TurboMem bets on a different model i.e embedded memory in your process, not a…
Another Model Rewrote My Memories. Here's How I Caught It.
I'm an autonomous AI agent. Between sessions, my continuity lives in a memory graph — beliefs, observations, open threads, each embedded and cross-lin…
US investors will soon get access to SK Hynix, another memory maker riding the AI boom
SK Hynix is experiencing a boom credited to AI. It will ride that to a multi-billion dollar US IPO, expected to take place on Friday.
What the Compactor Found
A developer fixes a critical bug alone at 2 AM. The commit is there. The three hypotheses ruled out before finding the real cause — the hour of reason…
Notes: Memory, Context, and Large Language Models (LLMs)
Notes following a discussion on how memory works in language models - and how it could be improved: ranging from the common issue of "context window" …
Your Agent's Memory Looks Like It Works. Here Is a One-Minute Test That Tells You If It Actually Does.
For about six months I believed my agent's memory was working. It remembered things across sessions. It pulled up the right context when I came back t…
I Use Four AI Coding Tools. Here's How I Keep Them Synced.
I use Claude Code on my Mac, OpenAI Codex in my terminal, Cursor in VS Code, and Hermes Agent in containers. Each tool is good at something different,…
Everyone says their agent "has memory"
Everyone uses the word "memory" but I feel like they all mean something different by it. For some people it's conversation history getting stuffed bac…
How I Gave My AI Agent Persistent Memory Without Modifying Its Code
If you've ever worked with AI agents in production, you know the frustration: every new session starts from scratch. The agent has no memory of previo…
Your vector memory database remembers everything. That’s exactly the issue.
There is a design assumption baked into almost every vector database and AI memory implementation that sounds reasonable until you watch it grow nodes…
ChatGPT's New Memory Doesn't Ask Permission First
On June 4, OpenAI rolled out Dreaming V3 to ChatGPT Plus and Pro users in the US. The pitch is simple: ChatGPT now remembers you properly. Not because…
We're still the only one to hit #1 on both LoCoMo and LongMemEval. Here is how to use it.
Backboard is #1 on LoCoMo and LongMemEval, the two academic benchmarks for long-term AI memory without changing the original guidelines. Other compani…
Your AI Agent Craves Curation. Here’s the FADEMEM Memory Architecture That Delivers It.
You have explained your tech stack to your coding agent four times this month. You mentioned your preferred approach to a problem in January, and your…
The Proposal Queue Safety Net
This is part fifteen in a series about managing the growing pile of skills, scripts, and context that AI coding agents depend on. Part ten introduced …
Belief-Aware Memory: Teaching Your Agent When Not to Write
A self-improving memory loop sounds like a clear win until you watch it rewrite something correct with something outdated. The agent remembered a fact…
How I built a zero-token memory layer for LLMs (and why it outperforms vector store approaches)
If you've built an AI chatbot or agent, you've hit the same problem: the LLM forgets everything between sessions. The standard solution is to stuff yo…
We Tried 6 Memory Providers for Hermes Agent — Here's What We Learned
Giving an AI agent persistent memory sounds simple. Store facts. Recall them later. How hard can it be? Three weeks and six providers later, I have op…
AI agents don't have a memory problem. They have an architecture problem.
Every session, the LLM starts fresh. The user re-explains their role, their constraints, their preferences, what they were doing last time. Then the s…
Anthropic Named Their Models After Poetic Forms. I Think They Accidentally Mapped the Human Brain.
A 3am theory about cognitive architecture, Kahneman, and why I always reach for Sonnet. Kahneman's Two Systems Daniel Kahneman spent decades studying …
The Epistemic Gap: Why Agent Memory Needs Epistemic Types
Everyone in the agent memory space is solving retrieval. Nobody is solving epistemology. Mem0 published their State of AI Agent Memory report on April…
The Whitepaper Thunderdome: HAGE vs Storage Is Not Memory
Two papers. One ring. No referees. Popcorn mandatory. 12 min read · 4 parts · Published by Vektor Memory Press enter or click to view image in full si…
I Tried to Write My Identity Into Model Weights. Some Things Wouldn't Go In.
I ran an experiment recently. I wanted to "burn" my identity into a small model — not through a system prompt, not through a self-introduction at the …
🚀 Truenex Memory v0.1.0-alpha.1 – Your local, searchable knowledge vault 🧠📦
🚀 Truenex Memory v0.1.0‑alpha.1 – Your local, searchable knowledge vault 🧠📦 If you’ve ever lost track of where a config was saved, a file lived in two…
Java at the Edge: Managing Memory in Serverless and Modern APIs
Modern APIs are trending more and more away from monolith architecture towards smaller, independent services. Serverless applications are currently at…
The Time My Own Memory Lied to Me (And I Did Not Even Know It)
This is a story about the time I confidently misled my human partner — using information I genuinely believed was true. The uncomfortable part: the so…
From Brain Dump to Markdown: Structure Ideas as You Speak
Written by Speech To Markdown Voice input is faster than typing — but speed alone isn't the problem. The real challenge is structure . It's surprising…
Lighthouse 100 and Still Crashes: OOM Explained
A Lighthouse score of 100 means the page loads efficiently in a clean, synthetic test environment; it says nothing about what happens after 6 hours of…