Every bookmark, follow and subscription was you deciding whose thinking is worth your time. Opyt turns that into a knowledge base that keeps growing, accessible from the AI you already use. No new app. It pulls in new work from the people you already read and the topics you keep coming back to.
Sources
Point Opyt at the sources you already use: X, Substack, GitHub, research papers, blogs, and article pages you hand it. The saving, following and subscribing you already do is the input, and everything they publish ends up in one place you can search.
Start with one source you already use. Opyt explains each connection and waits for your choice before it reads anything.
you › I want to set Opyt up.
claude › Everything you saved is in. 703 posts are now searchable, and Opyt knows the 1,193 accounts they came from.
You do not have to remember who is worth listening to. Your platform engagement already records it, and Opyt counts it up.
Opyt pulls someone's whole archive, going back years, not the three posts you happened to bookmark.
What it reads
| X | bookmarks · likes · follows · Lists | your connected OPYT-managed session |
|---|---|---|
| Substack | follows · subscriptions · saved posts, available full text | your connected OPYT-managed session |
| GitHub | a tracked person's repos and READMEs | public |
| Blogs | a tracked person's whole archive, found by feed or sitemap | public |
| arXiv · OpenAlex | papers matching your standing questions; tracked OpenAlex authors and research venues | public |
| A link you hand it | a supported paper, post, article or repo | you |
| posts and articles from the people you track | coming soon |
| Aggregators | Hacker News · Hugging Face · npm · crates.io · Stack Overflow · Product Hunt · Homebrew | coming soon |
|---|---|---|
| Funding | company and round data, asked by name | coming soon |
Automatic growth
Interact with your topics the way you already do with AI. Opyt organizes what you save, reads a topic through, and writes its own questions from it, then keeps them running against arXiv, GitHub and OpenAlex. New work on your topics is already there when you go looking, with nothing for you to set up or refresh.
Your library gets better on the days you never open it.
Eleven things about how agents should keep memory arrive in your store: bookmarks, a Substack thread, two papers. You were reading, not filing.
you › Read everything I've saved on how agents keep memory.
⚙ sitting(action="read")
claude › Ninety-six items, fourteen authors, oldest first. That read left three questions running, none typed by you. Here is one:
claude › That question caught letta-ai/letta, agents whose memory edits itself. It is in your store now, and the topic is seven items bigger than the day you read it.
you › Read everything I've saved on data-center grid costs.
codex › Read the whole topic end to end, oldest first. Three questions came out of that read and they are still running. You typed none of them:
you › Anything new?
codex › Six things came in since Tuesday, ranked by how many of your own questions reached each one:
Retrieval
No new app, no chat UI. A local install is a plain MCP server, so anything that speaks MCP to a local process can read your local store: Claude Code, Claude Desktop, Cursor, Codex, Windsurf, etc. Claude.ai can instead use Opyt's hosted connector. Your client does the reasoning on the subscription you already pay for.
you › Are tariff price effects one-off or recurring?
⚙ search("are tariff price effects one-off or recurring")
claude › Three of your own sources speak to this. The closest is a post you bookmarked yourself in June:
you › Read everything I've got on GLP-1 drugs and muscle loss, and lay out what it actually claims.
⚙ sitting(action="read", lens="claims")
claude › Eleven claims came back, each paired with what would break it and each citing the documents it came from. The first three:
you › Brief me on that topic. What do the documents actually establish?
⚙ sitting(action="lens", lens="briefing")
claude › Across 47 documents: what holds, what is still open, and where your authors converge.
you › How has the thinking on this changed over time?
⚙ sitting(action="lens", lens="trajectory")
claude › Three phases, in publication order. What your sources argued in 2024 is not what they argue now:
you › Argue against this using only my own sources: muscle loss is the main risk of these drugs.
⚙ sitting(action="lens", lens="disconfirmation", claim=…)
claude › Two direct counters from your material, and one place where it cannot attack the claim at all:
you › Does resistance training during treatment preserve lean mass?
⚙ sitting(action="lens", lens="gaps", claim=…)
claude › Your material does not answer it. The two nearest things, with why each falls short:
you › Save this: arxiv.org/abs/2608.01144
you › yes
claude › Saved in full text, searchable beside everything else.
Saving something is one sentence. No folders, no tags, no deciding where it belongs.
Collaboration
Reading from someone else's knowledge base is frictionless, so you can learn and build off each other's interests. One question reaches everyone who shared theirs with you.
you › I need to pick an eval setup for retrieval. Has anyone already been through this?
⚙ search("evaluating retrieval quality", kb="ana")
⚙ search("evaluating retrieval quality", kb="ravi")
⚙ search("evaluating retrieval quality", kb="priya")
claude › Two of them have. Ana read the framework and its repo in March, and Ravi has the benchmark it is usually compared against. Nothing on this in yours:
Sharing sends the whole knowledge base to a copy Opyt hosts, and it
stays readable until you take it back.
unshare
cuts off one reader, or every reader plus that copy. It goes one way: accepting gives
you read access and gives them nothing, and what the service records is that you read,
never what you searched for.
Calls
Opyt is free and MIT-licensed. On hosted Opyt, model access is covered by Opyt — nothing per-user to run out of. On a local install Opyt covers model costs to start with, and helps you authorize your own OpenRouter account when that runs out. Reading images needs your own OpenRouter account on either path.
| Your AI client | every question, every answer, all the reasoning | your configured client |
|---|---|---|
| OpenRouter | sorting, extracting, and embedding | access covered by Opyt, or your own authorized account |
| X | posts, timelines, profiles, threads | your OPYT-managed browser session |
| Substack | subscriptions, saved posts, full text | your OPYT-managed browser session |
| Everything else | papers, blogs, GitHub, supported article pages | public source access |
Install
Pick your client.
Nothing to download, no terminal. Claude.ai reaches a hosted Opyt over the internet, so this works on any computer, on every plan including free.
https://mcp.useopyt.com/mcp
This is an address you paste, not a page you visit. Opening it in a browser shows a blank page or an error — that is what it is supposed to do.
Opyt if
it asks for a name. Leave Advanced settings alone — Opyt needs no client ID and
no secret.onboard. Opyt can set up model access using your
existing sign-in. Choose a source — X, Substack, research, a personal site, or skip —
and decide what to import and keep current. X and Substack connect through a private
browser desktop; enter Substack's emailed code there. Nothing is pasted into chat.The hosted home is its own store: it is not the local
~/.opyt database, and it reads nothing on your computer. Use Claude Desktop,
Claude Code, Cursor or Windsurf when you want the local installation.
Nothing to download, no terminal — the same hosted Opyt claude.ai uses. ChatGPT keeps custom connectors behind developer mode, and it needs a paid plan: Plus, Pro, Business, Enterprise or Edu. Free accounts cannot add one.
https://mcp.useopyt.com/mcp
An address you paste, not a page you visit. Opening it in a browser shows a blank page or an error — that is what it is supposed to do.
Opyt, write any
description, and paste the address into MCP server URL.onboard. Opyt can set up model access using your
existing sign-in, then asks for a first source and import consent. X and Substack
connect through a private browser desktop; enter Substack's emailed code there.
Follow the setup prompts to choose who to track.This is the same hosted store claude.ai gets, and the same Google
sign-in reaches it from either one. It is not the local ~/.opyt database.
Without typing anything. Download this and open it —
it unzips to opyt-install.command. Then right-click that and choose
Open, not a double-click: macOS blocks anything downloaded until you approve it
once that way. Terminal opens, asks which app you want, and installs Opyt into it.
Or run this yourself, which is what that file does:
This merges Opyt into ~/.cursor/mcp.json beside
whatever servers are already there, and copies the old file aside first. Running it
twice changes nothing, and --uninstall removes the entry and leaves the
rest.
This merges Opyt into
~/.codeium/windsurf/mcp_config.json beside whatever servers are already
there, and copies the old file aside first. Running it twice changes nothing, and
--uninstall removes the entry and leaves the rest.
uv, then run which uvx in a
terminal to get its absolute path:
Absolute, not a bare uvx: a desktop app never
reads your shell profile, so it will not find uvx on the PATH.
A restart is also how you get fixes. The command above says
opyt@latest, so your client resolves the newest published Opyt every time
it starts one — there is no upgrade step and nothing to re-run. Offline it keeps
running the copy you already have.
It starts at login, opens no port, and holds no credential of
its own. --uninstall removes it. If you installed with
opyt-install.command, this already ran — running it again changes
nothing.
onboard. Follow the sign-in or account-approval step
it offers, then choose a source — X, Substack, research, a personal site, or skip —
and decide what to import and keep current. Nothing is pasted into chat.Hand this to the client you want Opyt in and it does the whole thing:
> Install the Opyt MCP server for this client, from useopyt.com/docs.html.
Opyt's free and MIT-licensed. If it's useful to you, star it. That's how other people find it.