It remembers
Your apps save what matters as you work: decisions, preferences, project facts, open questions. Next session they still know, so you stop re-explaining.
Shared memory for Claude, Codex and your agents
Give your AI apps and agents one long-term memory they all share. Tell one about a decision and the others already know it. It's plain Markdown you own, and setup is one URL.
Free tier. No card, no invite, no queue.
Aisle one / What it does
It isn't a chatbot or a notes app. It's one memory your AI apps connect to, so what you work out with one of them is there for all of them.
Your apps save what matters as you work: decisions, preferences, project facts, open questions. Next session they still know, so you stop re-explaining.
Claude, Codex and any app that speaks MCP read the same memory. Switch tools, or hit a usage cap, and your context comes with you.
What worked becomes a skill your agents load before they start. You approve every one, and each agent gets only the skills and permissions you give it.
Aisle two / Getting started
Nothing to install and nothing to import. You add one address to the AI apps you already use.
Paste it into your AI app's connector settings. Steps for Claude, Codex and others are below.
https://openbrainstore.com/mcpThat's your account. The free tier starts right away: no card, no invite, no new password.
Your apps save what matters as you go and look it up when it helps. Ask one app what another learned.
Aisle three / See it work
Two different apps, one account. A decision saved in one is an answer in the other.
In Claude · it saves
Remember: our retrieval uses vectors only as a fallback.
In Codex · it recalls
What retrieval strategy did we choose?
Filters and full text first, then linked memories. Vectors only when those come up short.
Same account. Different app. No copy and paste.
Aisle four / Skills New
Memory is what your agents know. Skills are how you want things done: checklists, procedures and guardrails built from work that went well. Every skill is versioned, and none reaches an agent until you approve it.
After a task goes well, an agent drafts a skill from it: your deploy checklist, how you review a pull request, a rule it should never break.
Drafts wait in the Catalog tab of the app. Edit, approve or reject them. Agents can never approve their own.
At the start of a session, each agent gets the skills that fit its task and fetches the ones it needs.
Agent profiles give an agent its own role, skills and key, with only the permissions you pick. Change or revoke a key from the app; nothing new needs pasting into the agent.
Skills are opt-in: turn them on in the app's Catalog tab. Memory works the same either way.
Aisle five / Why it matters
The more an AI app learns about you, the harder it is to leave. Your context turns into someone else's switching cost.
Today · a memory per app
With OpenBrainStore · one memory
Max out one subscription, switch to another AI app, and keep going with the same project history. Your usage resets. Your context doesn't.
Aisle six / Finding things again
Any agent can drop notes in a folder. Finding them again is the hard part: ask about "auth decisions" and the note that says "OAuth and PKCE" never comes back.
OpenBrainStore keeps the same plain files underneath and does the librarian's job on top. Names and tags are tidied on the way in, so they agree no matter which agent wrote them. Every recall says which drawer found the answer.
Watch a recall thinkEvery recall opens these in order
Type, tags, people and projects, dates, key-values.
The words you actually wrote, matched fast.
Related notes one or two links away, like the reasoning behind a decision.
Meaning, not just words, across everything you've stored. Opens on its own when the first three come up short, or whenever an agent asks.
Aisle seven / Yours to keep
Every memory is a plain Markdown file in an open format, the Open Knowledge Format, not a row locked inside one vendor's app. Read them, export them, or run the same server yourself.
--- type: decision tags: [retrieval, architecture] entities: [openbrainstore] links: [mem_01KXVZ…] created: 2026-07-19 --- Retrieval runs structured filters and full text first, then graph context. Vectors run only as a fallback.
Readable, diffable files with a few lines of front matter, indexed four ways so owning your files never means grepping them.
The open protocol AI apps already use to connect tools. No special SDK.
Access belongs to your account, not to an app or a session, so every app reaches the same memory.
Export the files whenever you like, or run the same server on infrastructure you control.
Aisle eight / Identity and trust
Every request is tied to your GitHub account. Apps and agents only get access you can see and take back.
Your account is GitHub's numeric user ID, so changing your username never cuts you off from your memory.
Apps connect with OAuth 2.1 and PKCE. No client secrets to hand around.
Apps get rotating tokens. Agents get their own keys: limited to what you pick, set to expire, and changeable any time.
Export the Markdown or run the service yourself. The format doesn't depend on us.
Aisle nine / Two ways in
Both paths share one open format and one open protocol, so there's no lock-in, even into us.
Run your own instance, with full control and no cost beyond your own infrastructure. Free for individuals and companies under $1M a year.
We run the same server for you, signed in with your GitHub account. The free tier starts the moment you sign in.
Aisle ten / Pricing
No seats and no meters on recall. Export everything, on either plan, any time.
We'll email you the day Pro opens. Meanwhile, the free tier is live right now, and everything you store today comes with you when you upgrade.
Aisle eleven / Connect an app
These are the real steps, and they work now. Signing in with GitHub creates your free account on the spot.
Open Settings, then Connectors, then Add custom connector. Leave Client ID and Secret empty. GitHub finishes the sign-in in your browser.
Name: openbrainstore
Remote MCP server URL:
https://openbrainstore.com/mcp
OAuth Client ID / Secret: leave emptyAdd the server to your Codex config, then log in. A browser window finishes the GitHub sign-in.
Your GitHub identity is the account. There's no separate signup step.
[mcp_servers.openbrainstore]
url = "https://openbrainstore.com/mcp"
codex mcp login openbrainstoreAdd the URL in your app's MCP settings (Streamable HTTP). Sign-in is discovered automatically: registration, authorization and token metadata.
Leave credentials empty if your app supports dynamic registration.
Remote MCP URL:
https://openbrainstore.com/mcp
OAuth: automatic discovery
Scope: memoryThe open format underneath OpenBrainStore. Every memory is a Markdown file with a little front matter: typed, tagged, linked to people and projects, and tied to your account rather than to any AI vendor. You can read it, diff it, export it and run it anywhere. OpenBrainStore is the first OKF service: the memory layer.
Same files underneath, different job. A vault is for you to garden and search, and you carry context into your AI by hand. OpenBrainStore is a memory your AI apps write to mid-conversation and search for you, over MCP. You can still open every file; nobody has to garden them.
No. Exact filters and full text run first, linked memories add context, and deep semantic search runs when those come up short or an agent asks for it.
No. Tidying names, tags and types is deterministic. The memory itself is the plain text your app sends.
Yes, when both are signed in as you. Your account decides what they can reach; the app and the session don't.
Reusable instructions for your agents: a checklist, a procedure, a guardrail. Agents propose them, you approve them in the app, and agents load the ones that fit their task at the start of a session. Assign skills to an agent profile and only that agent sees them. Skills are opt-in and versioned, and agents can never approve their own.
Apps like Claude and Codex sign in with GitHub and don't. Agents that run on their own, like scheduled jobs, CI or your own code, use a key from the app's Agents tab: limited to the permissions you choose, optionally bound to an agent profile, set to expire, and changeable or revocable any time.
Export the Markdown files and run the same server yourself. Local disk and S3-compatible storage keep the same portable structure.
It disappears from search and the graph right away. The file itself is kept for a short grace period before it's purged for good, so a mistake can be recovered.
Claude and Codex are verified end to end. Other apps work if they support remote MCP servers with OAuth (Streamable HTTP).
Aisle thirteen / Get in touch
OpenBrainStore is free to self-host for individuals and companies under $1M in yearly revenue (PolyForm Small Business license). Bigger, or want to offer it as a hosted service? Let's talk about a commercial license.
Thanks for reaching out. We'll get back to you at the email you gave.
Bring your memory with you when it does.