diff --git a/backend/alembic.ini b/backend/alembic.ini
new file mode 100644
index 0000000..fc9ea7b
--- /dev/null
+++ b/backend/alembic.ini
@@ -0,0 +1,147 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library and tzdata library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = %(DATABASE_MIGRATE_URL)s
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S
diff --git a/backend/migrations/README b/backend/migrations/README
new file mode 100644
index 0000000..e0d0858
--- /dev/null
+++ b/backend/migrations/README
@@ -0,0 +1 @@
+Generic single-database configuration with an async dbapi.
\ No newline at end of file
diff --git a/backend/migrations/env.py b/backend/migrations/env.py
new file mode 100644
index 0000000..0036b4e
--- /dev/null
+++ b/backend/migrations/env.py
@@ -0,0 +1,103 @@
+import asyncio
+import os
+from logging.config import fileConfig
+
+from sqlalchemy import pool
+from sqlalchemy.engine import Connection
+from sqlalchemy.ext.asyncio import async_engine_from_config
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Inject the runtime DSN from the OS environment.
+# %(DATABASE_MIGRATE_URL)s interpolation in alembic.ini only works when the variable
+# is defined in the [alembic] section — it does NOT read from the OS environment.
+# We override sqlalchemy.url here so that the env var is honoured at runtime.
+config.set_main_option(
+    "sqlalchemy.url",
+    os.environ.get(
+        "DATABASE_MIGRATE_URL",
+        config.get_main_option("sqlalchemy.url") or "",
+    ),
+)
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# Import all models so that Base.metadata is populated for autogenerate support.
+# This MUST happen before target_metadata is assigned — Alembic won't see tables
+# that haven't been imported (RESEARCH.md Pitfall 2).
+from db.models import Base  # noqa: F401 — must import to register all models (Pitfall 2)
+
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def do_run_migrations(connection: Connection) -> None:
+    context.configure(connection=connection, target_metadata=target_metadata)
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    """In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    connectable = async_engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+
+    await connectable.dispose()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode."""
+
+    asyncio.run(run_async_migrations())
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()
diff --git a/backend/migrations/script.py.mako b/backend/migrations/script.py.mako
new file mode 100644
index 0000000..1101630
--- /dev/null
+++ b/backend/migrations/script.py.mako
@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}
diff --git a/backend/migrations/versions/0001_initial_schema.py b/backend/migrations/versions/0001_initial_schema.py
new file mode 100644
index 0000000..b418fc0
--- /dev/null
+++ b/backend/migrations/versions/0001_initial_schema.py
@@ -0,0 +1,257 @@
+"""Initial v1 schema — all 11 DocuVault tables.
+
+Revision ID: 0001
+Revises:
+Create Date: 2026-05-22
+
+Creates tables in dependency order:
+  1. users              (no FK dependencies)
+  2. groups             (no FK dependencies — D-02 stub)
+  3. quotas             (FK -> users)
+  4. refresh_tokens     (FK -> users)
+  5. folders            (FK -> users, self-referential FK -> folders)
+  6. topics             (FK -> users)
+  7. documents          (FK -> users [nullable, D-03], FK -> folders)
+  8. document_topics    (FK -> documents, topics)
+  9. shares             (FK -> documents, users x2)
+ 10. audit_log          (FK -> users x2)
+ 11. cloud_connections  (FK -> users)
+
+Pitfall 4 note: ALTER DEFAULT PRIVILEGES is required so future migrations
+(applied by docuvault_migrate) automatically grant access to docuvault_app.
+The docuvault_app user is created in docker/postgres/initdb.d/01-init-users.sql
+with CONNECT but no table privileges — this migration grants them.
+"""
+from __future__ import annotations
+
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "0001"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ── 1. users ──────────────────────────────────────────────────────────────
+    op.create_table("users",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("handle", sa.String(), nullable=False),
+        sa.Column("email", sa.String(), nullable=False),
+        sa.Column("password_hash", sa.Text(), nullable=False),
+        sa.Column("totp_secret", sa.Text(), nullable=True),
+        sa.Column("totp_enabled", sa.Boolean(), nullable=False, server_default="false"),
+        sa.Column("role", sa.String(), nullable=False, server_default="user"),
+        sa.Column("is_active", sa.Boolean(), nullable=False, server_default="true"),
+        sa.Column("ai_provider", sa.Text(), nullable=True),
+        sa.Column("ai_model", sa.Text(), nullable=True),
+        sa.Column("default_storage_backend", sa.String(), nullable=False, server_default="minio"),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("handle"),
+        sa.UniqueConstraint("email"),
+    )
+
+    # ── 2. groups (D-02 stub — v2 feature) ───────────────────────────────────
+    op.create_table("groups",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("name", sa.Text(), nullable=False),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+
+    # ── 3. quotas ─────────────────────────────────────────────────────────────
+    op.create_table("quotas",
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=False),
+        # 100 MB default free-tier quota
+        sa.Column("limit_bytes", sa.BigInteger(), nullable=False, server_default="104857600"),
+        sa.Column("used_bytes", sa.BigInteger(), nullable=False, server_default="0"),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("user_id"),
+    )
+
+    # ── 4. refresh_tokens ─────────────────────────────────────────────────────
+    op.create_table("refresh_tokens",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("token_hash", sa.Text(), nullable=False),
+        sa.Column("expires_at", sa.TIMESTAMP(timezone=True), nullable=False),
+        sa.Column("revoked", sa.Boolean(), nullable=False, server_default="false"),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("token_hash"),
+    )
+    op.create_index("ix_refresh_tokens_user_revoked", "refresh_tokens", ["user_id", "revoked"])
+
+    # ── 5. folders ────────────────────────────────────────────────────────────
+    op.create_table("folders",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("parent_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("name", sa.Text(), nullable=False),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["parent_id"], ["folders.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("user_id", "parent_id", "name", name="uq_folders_user_parent_name"),
+    )
+
+    # ── 6. topics ─────────────────────────────────────────────────────────────
+    op.create_table("topics",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("name", sa.Text(), nullable=False),
+        sa.Column("description", sa.Text(), nullable=False, server_default=""),
+        sa.Column("color", sa.String(7), nullable=False, server_default="#6366f1"),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("user_id", "name", name="uq_topics_user_name"),
+    )
+
+    # ── 7. documents ──────────────────────────────────────────────────────────
+    op.create_table("documents",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        # D-03: user_id is nullable in Phase 1 — no auth yet.
+        # Phase 2 migration adds NOT NULL constraint.
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("folder_id", postgresql.UUID(as_uuid=True), nullable=True),
+        # original human-readable filename — stored in DB only, never in the MinIO key
+        sa.Column("filename", sa.Text(), nullable=False),
+        # MinIO object key: {user_id}/{document_id}/{uuid4()}{ext}
+        sa.Column("object_key", sa.Text(), nullable=False),
+        sa.Column("content_type", sa.Text(), nullable=False),
+        sa.Column("size_bytes", sa.BigInteger(), nullable=False, server_default="0"),
+        sa.Column("storage_backend", sa.String(), nullable=False, server_default="minio"),
+        sa.Column("extracted_text", sa.Text(), nullable=True),
+        sa.Column("status", sa.String(), nullable=False, server_default="pending"),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.Column("updated_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["folder_id"], ["folders.id"], ondelete="SET NULL"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index("ix_documents_user_folder", "documents", ["user_id", "folder_id"])
+    op.create_index("ix_documents_user_created", "documents", ["user_id", "created_at"])
+
+    # ── 8. document_topics ────────────────────────────────────────────────────
+    op.create_table("document_topics",
+        sa.Column("document_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("topic_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.ForeignKeyConstraint(["document_id"], ["documents.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["topic_id"], ["topics.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("document_id", "topic_id"),
+    )
+
+    # ── 9. shares ─────────────────────────────────────────────────────────────
+    op.create_table("shares",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("document_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("owner_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("recipient_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("permission", sa.String(), nullable=False, server_default="view"),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.ForeignKeyConstraint(["document_id"], ["documents.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["owner_id"], ["users.id"], ondelete="CASCADE"),
+        sa.ForeignKeyConstraint(["recipient_id"], ["users.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("document_id", "recipient_id", name="uq_shares_document_recipient"),
+    )
+    op.create_index("ix_shares_recipient", "shares", ["recipient_id"])
+
+    # ── 10. audit_log ─────────────────────────────────────────────────────────
+    op.create_table("audit_log",
+        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("actor_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("event_type", sa.Text(), nullable=False),
+        sa.Column("resource_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("ip_address", sa.dialects.postgresql.INET(), nullable=True),
+        # DB column name is "metadata"; ORM uses "metadata_" to avoid reserved-attr conflict
+        sa.Column("metadata", sa.dialects.postgresql.JSONB(), nullable=True),
+        sa.Column("created_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="SET NULL"),
+        sa.ForeignKeyConstraint(["actor_id"], ["users.id"], ondelete="SET NULL"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index("ix_audit_user_created", "audit_log", ["user_id", "created_at"])
+    op.create_index("ix_audit_event_created", "audit_log", ["event_type", "created_at"])
+
+    # ── 11. cloud_connections ─────────────────────────────────────────────────
+    op.create_table("cloud_connections",
+        sa.Column("id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=False),
+        sa.Column("provider", sa.String(), nullable=False),
+        sa.Column("display_name", sa.Text(), nullable=False),
+        sa.Column("credentials_enc", sa.Text(), nullable=False),
+        sa.Column("status", sa.String(), nullable=False, server_default="ACTIVE"),
+        sa.Column("connected_at", sa.TIMESTAMP(timezone=True), nullable=False, server_default=sa.text("now()")),
+        sa.ForeignKeyConstraint(["user_id"], ["users.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index("ix_cloud_connections_user", "cloud_connections", ["user_id"])
+
+    # ── Privilege grants ───────────────────────────────────────────────────────
+    # Pitfall 4: ALTER DEFAULT PRIVILEGES is required so future migrations
+    # (applied by docuvault_migrate user) automatically grant DML access to
+    # docuvault_app on any tables created afterward.
+    #
+    # The docuvault_app user is created in docker/postgres/initdb.d/01-init-users.sql
+    # with CONNECT privilege only — no table-level access. These two grants establish:
+    #   (a) immediate access to all tables/sequences created by THIS migration
+    #   (b) automatic access to all tables/sequences created by FUTURE migrations
+    #       run by the same docuvault_migrate user
+    op.execute("GRANT SELECT, INSERT, UPDATE, DELETE ON ALL TABLES IN SCHEMA public TO docuvault_app;")
+    op.execute("ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT SELECT, INSERT, UPDATE, DELETE ON TABLES TO docuvault_app;")
+    # Sequences grant is required because audit_log.id uses a sequence (autoincrement).
+    # docuvault_app must be able to call nextval() on any sequence.
+    op.execute("GRANT USAGE, SELECT ON ALL SEQUENCES IN SCHEMA public TO docuvault_app;")
+    op.execute("ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT USAGE, SELECT ON SEQUENCES TO docuvault_app;")
+
+
+def downgrade() -> None:
+    # Drop indexes first, then tables in reverse dependency order.
+
+    # cloud_connections
+    op.drop_index("ix_cloud_connections_user", table_name="cloud_connections")
+    op.drop_table("cloud_connections")
+
+    # audit_log
+    op.drop_index("ix_audit_event_created", table_name="audit_log")
+    op.drop_index("ix_audit_user_created", table_name="audit_log")
+    op.drop_table("audit_log")
+
+    # shares
+    op.drop_index("ix_shares_recipient", table_name="shares")
+    op.drop_table("shares")
+
+    # document_topics
+    op.drop_table("document_topics")
+
+    # documents
+    op.drop_index("ix_documents_user_created", table_name="documents")
+    op.drop_index("ix_documents_user_folder", table_name="documents")
+    op.drop_table("documents")
+
+    # topics
+    op.drop_table("topics")
+
+    # folders
+    op.drop_table("folders")
+
+    # refresh_tokens
+    op.drop_index("ix_refresh_tokens_user_revoked", table_name="refresh_tokens")
+    op.drop_table("refresh_tokens")
+
+    # quotas
+    op.drop_table("quotas")
+
+    # groups (D-02 stub)
+    op.drop_table("groups")
+
+    # users (last — all other tables depend on it)
+    op.drop_table("users")