Getting started with Mem just got easier! ✨
New onboarding is here in v0.10.117.
Choose where your data lives, connect your AI tools, and bring in your existing conversations.
Your context, ready from day one.
Huge thanks to @QuantumTransf and @wey_gu for making this happen!
Try it out: https://t.co/F2MBUHAbQL
3,200+ conversations, 1,000+ memories, and one shared memory across all your AI tools.
Love seeing how Carl puts Mem to work every day. Thanks for sharing such a thoughtful breakdown! 💙
I use about 5-6 different inference providers across 3-4 harness. This does not include the web interface I use from time to time.
What I find the most difficult to manage is my memory. They used to be fragmented to a point that I spent a lot of time finding the right conversation, copying pasting and all that.
I even tried to roll my own "2nd brain". Obsidian vaults and all those "skills". None worked nicely because if its something I have to even spend a minute thinking/managing, then it simply isnt good enough for me.
Also, as the chinese models improve i find that the most precious things are the years of conversations I have had with AIs and not the now commoditized "intelligence" that these models provide.
The retrieval is HIGHLY important - it makes no sense for AI to waste context reading .md files and trying to figure out where things stand. A graph database is preferred here:
About 6 months ago, Ava, our agentic sourcer notified me that someone is building this exact memory harness I was looking for: @nowledgemem (yes we are investors)
Here is my set up:
I've run every AI tool I use through @nowledgemem for months. 3,200+ conversations and 1,000+ memories later, here's what actually makes it great 🧵
One memory for every AI
MCP server + CLI + plugins. I use it in Claude Code (@claudeai), Codex (@OpenAIDevs), ChatGPT (@ChatGPTapp), Grok (@grok), DeepSeek (@deepseek_ai), Grok Bot and Muse.
Decide something in one tool, the next one already knows. No more re-explaining my setup. Its truly "hands off"
- It keeps the actual conversation
Full session threads are saved and searchable, not just AI-written summaries.
"What exactly did we decide last month?" gets the real transcript, not a guess.
- Search that finds both kinds of things
Hybrid search: BM25 keyword + vector embeddings in one query.
Finds the exact error code AND "that thing we talked about in October."
- It knows a rule from trivia
Every memory is typed (decision, procedure, preference, learning) and given an importance score.
"Stop asking me routine questions" follows me into every agent as a rule, not a buried note.
- Every chat starts already briefed
A session-start hook loads a daily Working Memory briefing into the agent.
New chat, zero setup. It already knows what I'm focused on.
- Receipts for every idea
Each memory links back to the tool and thread it came from.
It once caught that a research idea came from an old ChatGPT chat, not from me. That's trust.
- Local-first
The server runs on localhost and the data stays on my Mac. You can bring your own model keys.
My memory lives on my laptop, not in someone else's cloud.
- reachable when I choose
Remote MCP access protected by OAuth (mine goes through a Cloudflare tunnel).
Even cloud ChatGPT can use my local memory, behind a login, without exposing my machine.
- It draws its own map
It pulls out entities automatically (6,400+ for me) and groups them into topics (45).
My projects get organized without me tagging anything. Honestly I mostly use search, but it's a nice bonus.
The big one: a real 2nd brain, because it's a graph
Memories, conversations and entities are all linked. Mine has 6,400+ entities in 45 topics, built automatically.
Agents follow the links to the right decision instead of reading .md files. Like my brain, everything connects.
Last but not least: if an AI provider ever closes your account (important for my chinese fellows), you don't lose your history. Your conversations are already saved in your own memory.
We're heading to COSCon'26 this Sunday!
Our CEO Wey Gu will share his thoughts on open source and the knowledge layer at the Open Agent Ecosystem BoF.
See you in Hangzhou! Can't make it? Leave a question, and we'll bring it to the BoF.
https://t.co/QysqKdc436
A fresh look for Nowledge Mem! ✨
A cleaner sidebar, redesigned Threads, and more room for what matters.
Less noise. Same memories.
Take a look: https://t.co/fcZexzaV2A
Nowledge Mem is now in Slack! 🎉
Forgot what your team decided weeks ago? Just ask Mem to find the answer, right where the conversation happened.
Keep the context. Skip the digging.
Get started: https://t.co/ZRJfAYU2hW
HawDB v0.25.0 is out.
This release focuses on graph query execution, vector search, storage efficiency, and SQL support, along with MoonBit SDK improvements.
Special thanks to @colmugx for contributing MoonBit support!
HawDB v0.25.0 is out! In this release, we've added support for @moonbitlang . Huge thanks to @colmugx for the contribution! #HawDB#moonbit
https://t.co/zCHG0oWdoh
One integration, shared memory across your AI coding agents.
Magpie now supports Nowledge Mem, with automatic context recall and optional conversation history capture.
Huge thanks to @niuniu_8964 for making this happen! 🍬 🎃
Our co-founder & CEO @wey_gu is heading to AI Engineer Shanghai 2026!
He’ll be talking about Memory Engineering, RSI, and the Team Knowledge Layer.
If you're in Shanghai on Nov 5–6, come say hi! See you there. @aiDotEngineer
👺How to sync your message in @Muse to @NowledgeMem
Step 1: copy setup prompt to Muse
Step 2: Connect, Login and Allow Access
Step 3: Just waiting Muse setup itself
Step 4: Confirm your message in Nowledge Mem
https://t.co/nWPePBNYgg
Some things in life matter more than work.
When you need to be there for your family, you should be able to step away with peace of mind.
Your team has your back. And shared memory helps make that possible.