升目 masume
Keyboard-first terminal database client to browse, query and edit databases with AI chat.
Tested on Linux
Use it
Linux x86_64
These steps ran from a folder named work in the home folder, which already existed. Make it and run them from there:
mkdir -p "$HOME/work" && cd "$HOME/work"install masume via npm globally
npm install -g masume
Verified in pickfit: the commands exactly as its sandbox ran them
For the record only: they name the sandbox's home, /home/sbx.
npm install -g masume 2>&1masume --version 2>&1python3 -c "import sqlite3; con=sqlite3.connect('/home/sbx/work/notes.db'); cur=con.cursor(); cur.execute('DROP TABLE IF EXISTS notes'); cur.execute('CREATE TABLE notes(id INTEGER PRIMARY KEY, title TEXT, body TEXT)'); cur.executemany('INSERT INTO notes(title, body) VALUES (?,?)', [('hello','world'),('second','masume test')]); con.commit(); print(list(con.execute('SELECT * FROM notes')))"mkdir -p /home/sbx/.config/masume && cat > /home/sbx/.config/masume/config.toml <<'EOF'
[mcp]
profiles = ["notes"]
[profile.notes]
engine = "sqlite"
database = "/home/sbx/work/notes.db"
mode = "read-only"
EOF
cat /home/sbx/.config/masume/config.tomlmasume run ./notes.db -f csv 'select * from notes limit 100000' 2>&1Check that it works
masume --version 2>&1The output should contain “masume 0.0.17”.
First thing to try
python3 -c "import sqlite3; con=sqlite3.connect('$HOME/work/notes.db'); cur=con.cursor(); cur.execute('DROP TABLE IF EXISTS notes'); cur.execute('CREATE TABLE notes(id INTEGER PRIMARY KEY, title TEXT, body TEXT)'); cur.executemany('INSERT INTO notes(title, body) VALUES (?,?)', [('hello','world'),('second','masume test')]); con.commit(); print(list(con.execute('SELECT * FROM notes')))"mkdir -p "$HOME"/.config/masume && cat > "$HOME"/.config/masume/config.toml <<'EOF'
[mcp]
profiles = ["notes"]
[profile.notes]
engine = "sqlite"
database = "$HOME/work/notes.db"
mode = "read-only"
EOF
cat "$HOME"/.config/masume/config.tomlmasume run ./notes.db -f csv 'select * from notes limit 100000' 2>&1Run masume run <database file> -f csv '<your SQL>' to query a database file from the terminal.
What it does
- Browse and query databasesTested
How to use it
- Run
masume run <database file> -f csv '<your SQL>'to run a query against a database file. - Read the results printed as CSV rows.
- Run
- Chat with AI about the current connectionNot tested
- Share database profiles through an MCP serverNot shown working
How far pickfit got
Linux x86_64
- Installs
- Starts
- 1 of 3 features work
- Works offline
Good for
- browse database objects in the explorer
- run SQL queries and keep history
- export query results to CSV and JSON
- compare schemas of two connections
- serve database profiles to agents via MCP
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its main function works
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version masume 0.0.17
Differences the test machine hit
- README: masume --mcp --check checks enabled MCP profiles
In the test: create a config with [mcp] profiles=["notes"] and a [profile.notes] sqlite entry pointing at the db file; then it prints ok and exits 0