Give your agent a place to keep structured data. Pick up where you left off, in any chat or agent, and share the results as a link.
https://api.rho.store/mcpKeep
Your agent saves what it finds as a table with typed columns, under a name. Next week, another chat or another agent opens it and adds to it. A big table comes back as a summary and a sample, so the agent isn't swamped.
Check the licences in our vector database table.
Claude Code
Updated 2 rows. Version 3.
write_table("research/vector-dbs", rows, mode="upsert", key_columns=["name"])Reproduce
Save a query's result as a table, and rho remembers the query and the data it read. When that data changes, the table says so, and your agent reruns the query in one call. The earlier result is kept.
research/companies has this week's numbers. Rerun the high-growth list.
Claude
Refreshed from research/companies v3→v4. That's version 2; version 1 is kept.
refresh_table("research/high_growth")Undo
Every write is a new version, and old versions never change. A bad change is one restore away, and the restore is a version too. A delete goes to the trash.
That licence check was wrong. Put it back.
Claude Code
Restored version 2 as version 4. Nothing was lost.
restore_version("research/vector-dbs", version=2)Share
Make a table public and anyone with the link can open it, without signing in, and code can read it as an API. A figure can come with a receipt that shows the SQL behind it.
Send this to my colleague.
ChatGPT
Here's a link anyone can open.
share_table("research/vector-dbs")rho is an MCP server. Add its URL, sign in once, and your agent has its tools. There's no code to write.
The first ask needs an agent that can search the web: rho keeps the table, it doesn't browse.
Writing your own? There's a Python SDK, and every table has its ownAPI.
Drop a CSV, Excel, JSON or Parquet file into rho, and it's a table your agent can query. It also has a URL: rows as typed JSON, with filters, sorting and paging, and no server to run. A new upload is a new version at the same URL, and each version has a URL of its own that never changes. From Python, one call saves a DataFrame with its types.
curl https://api.rho.store/v/<key>?country=SE&sort=-pricerho.put(df, "research/sales")A sheet is made for people editing cells. rho is made for agents keeping tables.
The agent writes rows with typed columns. There's no sheet layout for it to keep straight.
It reads a summary and a sample, then asks SQL for the rest, rather than reading every cell.
Each write is a version, and the agent restores one in a single call.
Share the table with a person, or let code read it, from the same place.
A query saved as a table keeps its SQL, and runs again on new data in one call.
If people do most of the editing by hand, a spreadsheet is the better tool.
| Research your agent should keep and grow | rho |
| Results to pass between agents and people | rho |
| A SQL analysis to rerun as the data changes | rho |
| A file you want as an API | rho |
| A sheet people mostly edit by hand | a spreadsheet, such as Google Sheets |
| A one-off answer you won't come back to | a CSV in the chat |
| The database behind your app | a Postgres, such as Neon or Supabase |
| An agent's memory of text and facts | a memory store, such as Mem0 or Zep |