Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Saor.io – Persistent memory for AI agents, free, connects via MCP

saor.io

Post reply on HN
Print view View original

1–8 of 8 posts

Saor.io – Persistent memory for AI agents, free, connects via MCP

#1

Post by mrjaxon »

I built saor.io because I kept re-explaining my projects to Claude every morning. The AI had no memory between sessions. So I gave it one.

saor is a persistent brain layer for AI tools. You connect it via MCP with one command:

npx saor-mcp --setup --key sk_YOUR_KEY Once connected, your AI agents read and write memories automatically. Three tiers: identity (protected — only humans modify), operational (AI reads/writes freely), and ephemeral (auto-expires in 7 days).

Stack: Next.js, Supabase (Postgres/RLS), Claude Sonnet 4 for reasoning, Haiku 4.5 for bulk operations.

It's free. Unlimited brains, unlimited memories. The name saor means "free" in Irish. The per-brain infrastructure cost is negligible, so there's no reason to gate it.

Source of the MCP connector: https://github.com/saorio/saor-mcp

Curious what people think about the memory architecture — particularly the three-tier model and letting AI write to operational memory without approval gates.

Saor.io – Persistent memory for AI agents, free, connects via MCP
saor.io

Re: Saor.io – Persistent memory for AI agents, free, connects via MCP

#4

Post by mrjaxon »

mrsalty wrote: post #3

can you give a bit more details on how it works? what makes this different/better from main AI agent memory out there? the website is also quite cryptic

Fair feedback on the site — we probably went too minimal. Here's the mechanics:

*How it works:*

saor is a REST API + MCP server that stores structured context for AI agents. Not raw chat history — structured identity: who your business is, what your voice sounds like, what decisions you've made, what worked, what didn't.

1. You sign up, get an API key 2. Run `npx saor-mcp --setup --key sk_YOUR_KEY` in any project 3. Your AI tool (Claude Code, Cursor, etc.) now has 10 MCP tools: brain_context (read), brain_remember (write), brain_search (recall by tags), etc. 4. At session start, the AI loads your brain — identity, memories, constraints 5. As it works, it writes memories back — tagged, auto-linked 6. Next session, next tool, different AI entirely — same brain. Context compounds.

The brain is Postgres. No AI on our servers. Your AI tools do the thinking. We just store and serve the structured data.

*What's different from Mem0, Zep, etc:*

Most memory tools are key-value stores with vector search. Store a fact, recall a fact. Digital Post-it notes.

saor does three things they don't:

1. *Structured identity, not just memories.* Voice, audience, positioning, ethical constraints — a brain, not a notepad. Your AI doesn't just remember facts, it knows who it's working for.

2. *Knowledge graph.* Memories auto-link by tags. A "pricing" memory in one project connects to "pricing" in another. The graph builds itself — no manual linking.

3. *The brain teaches the agent.* Every context pack includes agent_instructions that tell the AI how to use the brain — read at start, write as you learn, tag for linking. The brain onboards every AI automatically. No CLAUDE.md needed.

It's free. Unlimited. The whole thing.

We'll make the site clearer — that's a fair hit.

Re: Saor.io – Persistent memory for AI agents, free, connects via MCP

#5

Post by mrjaxon »

mrsalty wrote: post #3

can you give a bit more details on how it works? what makes this different/better from main AI agent memory out there? the website is also quite cryptic

Let me know if what I've given you makes sense. I tend to "just do" what I need to have done, and while I understand the particulars of my needs, I don't generally need a roadmap for others...

Of note, I am working on the browser plugin. It should eliminate the need to work through the variable of "which site, which comms method" that we all navigate when we're involving more than one AI in a project.

Re: Saor.io – Persistent memory for AI agents, free, connects via MCP

#6

Post by mrjaxon »

mrsalty wrote: post #3

can you give a bit more details on how it works? what makes this different/better from main AI agent memory out there? the website is also quite cryptic

Thank you again for your feedback. I did listen, and I have updated the site significantly.

I had intentionally let the site be vague on particulars as I was hammering out backend issues.

One main issue that we discover for many AI is that they're not exactly "write" capable when it comes to certain tasks... Which makes the claim that it works with everything - partially true, but not to the extent that I want it.

That's where having a bridge via a plugin will be both essential and super scary. I've been thinking through all the various concerns and exploits that every plugin goes through and... wow. What a thing. After being completely paranoid and hypervigilant - I believe I have an elegant solution that satisfies my immediate terrors.

I'm not done fussing, but I'm close.

Thanks again.

Re: Saor.io – Persistent memory for AI agents, free, connects via MCP

#7

Post by mrsalty »

mrjaxon wrote: post #6
mrsalty wrote: post #3

can you give a bit more details on how it works? what makes this different/better from main AI agent memory out there? the website is also quite cryptic

Thank you again for your feedback. I did listen, and I have updated the site significantly. I had intentionally let the site be vague on particulars as I was hammering out backend issues. One main issue that we discover for many AI is that they're not exactly "write" capable when it comes to certain tasks... Which makes the claim that it works with everything - partially true, but not to the extent that I want it. Th…

Yes it makes more sense now. One thing I wonder, as most of memory systems this one also requires an LLM API key, what's the expected pricing involved? What does the LLM do here? I was looking into Cognee, one of the main players in the field, and they use YOUR tokens to summarise and chunk all your company data, which I expect to generate a hell of a token bill.
Post reply on HN