The edge-AI database for agents
Built in Europe

%% Open a database. Text is embedded into a vector on write.
{ok, _} = barrel:open(<<"notes">>, #{embedding => #{provider => openai}}).

%% One write stores the document, its vector, and its blobs under one id.
{ok, _} = barrel:put_doc(<<"notes">>, #{
    <<"id">>    => <<"n1">>,
    <<"title">> => <<"Design review">>,
    <<"text">>  => <<"Ship the edge sync protocol">>
}).

%% Query the document layer with BQL.
{ok, Rows, _} = barrel:query(<<"notes">>,
    <<"SELECT id, title FROM db WHERE title LIKE 'Design%'">>).

%% Search the vector layer over the very same records.
{ok, Hits, _} = barrel:query(<<"notes">>,
    <<"SELECT id, _score FROM vector_top_k('edge sync', k => 5) AS v">>).

# Run barrel_server for a REST/JSON and MCP surface over the same database.
$ curl -X PUT localhost:8080/db/notes
{"ok":true,"db":"notes"}

$ curl -X PUT localhost:8080/db/notes/doc/n1 \
    -H 'content-type: application/json' \
    -d '{"title":"Design review","text":"Ship the edge sync protocol"}'
{"id":"n1","ok":true,"rev":"0000019f46b4c08900000000@8c0010c983917d4b"}

# Vector search over the same records.
$ curl -X POST localhost:8080/db/notes/search/vector \
    -H 'content-type: application/json' -d '{"vector":[...],"k":5}'

# Agents speak MCP against the same endpoint.
$ curl -X POST localhost:8080/mcp -H 'content-type: application/json' -d '{...}'