Blog
Shared memory for teams and agents.
Guides on shared memory, MCP and AI agents, and what we're learning building Nysa.
What is shared memory for AI agents?
Shared memory is one store of facts, with sources, that every agent on a team reads from and writes to. Here is why agents forget, and what to look for.
Latest
Nysa's MCP tools, explained for developers
A walkthrough of the tools Nysa's MCP server exposes: meetings, people, companies, calendar and brain search. What each one returns and how to connect.
ProductHow Nysa keeps private email private while sharing what the team needs
Raw email stays private to its owner. The team gets the facts drawn from it, and each agent sees only what its teammate can see.
ProductHow Nysa turns meetings into facts with sources
Nysa's notetaker joins the calls you choose, then turns what was said into facts with the quote, date and source, so agents can check them.
GuideHow to prep for a customer call with your team's history and an AI agent
A five-step prep routine that uses an AI agent and your team's meetings, email and calendar, so you walk into every customer call knowing the history.
GuideHow to connect ChatGPT to your company's meetings, email and calendar
ChatGPT does not know what happened in your meetings or inbox. Here is how to connect it to that context with an MCP app, in three steps.
GuideHow to give Claude your team's meeting context
Three ways to get your team's meetings in front of Claude: paste, Projects, or a connector. What each does well, and how to set up the connector in minutes.
GuideHow to give every agent on your team the same company context
Each person's agent works from a different, partial picture of the company. Here is how to give all of them one shared source of facts.
Guide"Saved isn't searchable: how to check your agent actually has your team's context"
A saved meeting is not the same as one your agent can find. A five-minute checklist to test that your team's context is connected, processed and retrievable.
GuideShared memory is not shared access: scopes, sources and the current answer
A shared memory layer is only useful if every answer is scoped to the person asking, traceable to a source, and current. Here is what to check before you trust one.
GuideWhat does running agent memory actually cost? Setup, retries and upkeep
The real cost of agent memory is not just a bill. It is hosting, model usage, retries and the time of whoever keeps it running. Here is how to count each.
GuideShared agent memory without a server-maintenance side project
Self-hosting agent memory means you own installs, upgrades and config. Here is what that work looks like and how a managed setup removes it.
GuideSelf-hosted vs managed company brain: how to choose
Self-hosting gives control and costs engineering time. A managed brain gives speed, scoped access and sources. Here is a plain way to decide which fits.
GuideMCP explained for ops teams: how your agents connect to company context
MCP is the open standard that lets AI agents use outside tools and data. Here is how it works, who controls access, and where Nysa fits, in plain language.