Second Brain for AI

Persistent memory for Claude, ChatGPT & Cursor. Free.

Open Source

Developer Tools

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉Github ⧉YouTube ⧉

Second question! ( I separate it so you get more engagement! haha)

Could I connect this to a Raspberry Pi voice "flat mate" and use it as a shared memory layer?

So I can access to all my ChatGPT memory with that home device too?

Does this add continuity? Like timelime for the machine to understand that Its been 2 months I dont talk in that chat and It did not happen yesterday. I don't understand why is so difficult for ChatGPT to do this. I separate context in different chats...

I've been using persistent memory and cross memory between chats in chatGPT since last summer ( apparently I was an advance user or whatever, and It got activated before).

What I need is a TIME layer on it. Like timestamps / timeline awareness
Memory without time is incomplete.

Does this second brain fix this problem?

@rahilpirani Persistent memory across tools is something I keep running into as a builder. Does it work across different Claude/ChatGPT accounts or is it tied to the browser?

The 'every conversation starts from zero' problem is real — I waste so much time re-explaining project context to Claude Code every new session. Self-hosted is a big plus for me. Curious about the MCP integration — does it expose memory as a tool that the LLM can call dynamically, or is it more of a pre-prompt injection layer?

The forgetting problem is the actual bottleneck — not the quality of the model's reasoning. We've been building AI agents at Tuple for 18 months and the single biggest drop in usefulness happens at session boundary. A tool that routes around that without requiring the user to manage a "context file" is directionally correct. The self-hosted angle matters more than it might seem for B2B adoption — our clients will not put proprietary deal flow or client strategy into a vendor's cloud memory layer, full stop. Local or self-hosted is the only viable path there.

Memory as a separate product (rather than a feature of one chat client) is the right bet. The interesting bit is conflict resolution: when Claude and Cursor have both updated the same project entry over the last day with different framings, what wins? Last-write, semantic merge, or surfaced to the user? That choice usually decides whether the layer feels like trust or like noise after a few weeks of use.

the memory problem is so underrated in AI tooling right now. you spend 20 minutes setting up context in a conversation and then it just... vanishes. self-hosted is the right call too, especially for teams dealing with proprietary code. how does it handle conflicting memories across different tools?

The between-session memory problem is real and this solves it well. The harder problem - at least for how I use AI - is within-session overflow. My conversations regularly hit 100K+ words before they die/lag to unusble. The context window can't hold it all anyway, so even within a single session I'm losing early context. What I actually want is a rolling summarizer that compresses as the thread grows - keeping the essential through-line while shedding weight. That plus persistent cross-session memory would be the full solution. This a great idea tho, one I really like!

How does duplicate detection handle near-duplicates or nuanced variations in context? I've found that tricky in my own memory tools.

Quick update since launch. Here are a few things worth noting:
We shipped the Second Brain CLI today. If you use the terminal, you can now capture and recall memories without leaving it.

npm install -g second-brain-cf-cli

For those asking about integrations, Second Brain works with Claude, ChatGPT, Cursor, Windsurf, and any MCP-compatible client. There’s also an Obsidian plugin in the community directory, a Chrome extension, iOS Shortcuts in the repo, and a web UI if you prefer managing everything visually.

CLI, Obsidian, Chrome extension, iOS Shortcuts, MCP… same memory, every interface.

This is a strong wedge. The bit I’d be most careful with is treating “newer” as automatically more correct when memories conflict. For writing/product work especially, an old positioning decision might still be canonical while a recent one-off chat is just exploration.

A lightweight status layer could help a lot: canonical, draft, preference, deprecated, maybe source-linked. Then the model can say “I found the current rule” vs “I found a past note that may be stale,” instead of injecting both with the same confidence.

Semantic retrieval over stored context beats keyword search for memory, and the dedup layer is a smart addition since AI workflows generate a lot of overlapping notes. We've wrestled with context window management in multi-step AI tasks too: deciding when to summarize vs. fetch older context is genuinely tricky. How does the similarity threshold work when memories partially overlap? Can users tune it?

what the actual setup experience looks like for someone who knows their way around cloudflare but isn't a backend developer. the github readme is usually where these projects lose 80% of potential users because the instructions assume a level of comfort with wrangler and environment variables that most people who would benefit from this don't have. is there a one-click deploy path or is it still a manual configuration process

The product is good and very needed for those who want very personalised chats.

But even claude has a good context window not that big but decent

Nice one @rahilpirani !

This can be run on-prem too?

persistent memory is the piece most AI tools are missing right now. you end up re-explaining context every session which kills the usefulness for anything beyond one-off tasks. curious how this handles conflicting memories when your thinking evolves over time — does it version or just overwrite?

curious how it handles conflicting memories. if you store an architecture decision then change it a month later, does it override or accumulate? stale context injected confidently is probably worse than no context at all

how it's different than https://github.com/rohitg00/agen...