diff --git a/tests/test_balabit_adapter.py b/tests/test_balabit_adapter.py
index 436e22c..c8ff90f 100644
--- a/tests/test_balabit_adapter.py
+++ b/tests/test_balabit_adapter.py
@@ -9,7 +9,7 @@ import pytest
 
 def test_module_exports():
     """The adapter module must export the public functions used by CLI."""
-    from ai_mouse.data_adapters import balabit
+    from tools.data_adapters import balabit
     assert hasattr(balabit, "parse_session_csv")
     assert hasattr(balabit, "segment_by_clicks")
     assert hasattr(balabit, "filter_segments")
@@ -20,7 +20,7 @@ def test_module_exports():
 
 def test_mouse_event_dataclass():
     """MouseEvent has expected fields."""
-    from ai_mouse.data_adapters.balabit import MouseEvent
+    from tools.data_adapters.balabit import MouseEvent
     e = MouseEvent(t_ms=100, button="NoButton", state="Move", x=300, y=400)
     assert e.t_ms == 100
     assert e.state == "Move"
@@ -29,7 +29,7 @@ def test_mouse_event_dataclass():
 
 def test_segment_dataclass():
     """Segment has expected fields."""
-    from ai_mouse.data_adapters.balabit import MouseEvent, Segment
+    from tools.data_adapters.balabit import MouseEvent, Segment
     events = [MouseEvent(t_ms=0, button="NoButton", state="Move", x=10, y=20)]
     s = Segment(events=events, click_x=100, click_y=200, click_t_ms=500, session_id="user1_s1")
     assert s.events == events
@@ -45,7 +45,7 @@ def _write_csv(path: Path, rows: list[str]) -> None:
 
 class TestParseSessionCsv:
     def test_parses_basic_rows(self, tmp_path):
-        from ai_mouse.data_adapters.balabit import parse_session_csv
+        from tools.data_adapters.balabit import parse_session_csv
         csv = tmp_path / "session_1"
         _write_csv(csv, [
             "1500000000.000,0.000,NoButton,Move,100,200",
@@ -63,7 +63,7 @@ class TestParseSessionCsv:
 
     def test_handles_float_timestamps(self, tmp_path):
         """Client timestamps are floats in seconds; we convert to int ms."""
-        from ai_mouse.data_adapters.balabit import parse_session_csv
+        from tools.data_adapters.balabit import parse_session_csv
         csv = tmp_path / "session_2"
         _write_csv(csv, [
             "0,1.234,NoButton,Move,50,60",
@@ -75,7 +75,7 @@ class TestParseSessionCsv:
 
     def test_skips_malformed_rows(self, tmp_path):
         """Rows with bad data are logged and skipped, not raised."""
-        from ai_mouse.data_adapters.balabit import parse_session_csv
+        from tools.data_adapters.balabit import parse_session_csv
         csv = tmp_path / "session_3"
         _write_csv(csv, [
             "0,0.000,NoButton,Move,100,200",
@@ -89,7 +89,7 @@ class TestParseSessionCsv:
         assert events[1].x == 150
 
     def test_returns_empty_list_for_empty_file(self, tmp_path):
-        from ai_mouse.data_adapters.balabit import parse_session_csv
+        from tools.data_adapters.balabit import parse_session_csv
         csv = tmp_path / "session_4"
         csv.write_text("record timestamp,client timestamp,button,state,x,y\n", encoding="utf-8")
         events = parse_session_csv(csv)
@@ -98,11 +98,11 @@ class TestParseSessionCsv:
 
 class TestSegmentByClicks:
     def _make_event(self, t_ms: int, state: str, x: int, y: int, button: str = "NoButton"):
-        from ai_mouse.data_adapters.balabit import MouseEvent
+        from tools.data_adapters.balabit import MouseEvent
         return MouseEvent(t_ms=t_ms, button=button, state=state, x=x, y=y)
 
     def test_one_click_one_segment(self):
-        from ai_mouse.data_adapters.balabit import segment_by_clicks
+        from tools.data_adapters.balabit import segment_by_clicks
         events = [
             self._make_event(0, "Move", 10, 20),
             self._make_event(100, "Move", 50, 60),
@@ -120,7 +120,7 @@ class TestSegmentByClicks:
 
     def test_window_excludes_old_events(self):
         """Move events earlier than (click_t - window_ms) are dropped."""
-        from ai_mouse.data_adapters.balabit import segment_by_clicks
+        from tools.data_adapters.balabit import segment_by_clicks
         events = [
             self._make_event(0, "Move", 10, 20),       # too old
             self._make_event(100, "Move", 20, 30),     # too old
@@ -133,7 +133,7 @@ class TestSegmentByClicks:
         assert segments[0].events[0].t_ms == 900
 
     def test_multiple_clicks_multiple_segments(self):
-        from ai_mouse.data_adapters.balabit import segment_by_clicks
+        from tools.data_adapters.balabit import segment_by_clicks
         events = [
             self._make_event(0, "Move", 10, 20),
             self._make_event(100, "Pressed", 50, 50, button="Left"),
@@ -152,7 +152,7 @@ class TestSegmentByClicks:
 
     def test_skips_pressed_with_non_left_button(self):
         """Right-clicks and wheel-clicks don't anchor segments (only Left)."""
-        from ai_mouse.data_adapters.balabit import segment_by_clicks
+        from tools.data_adapters.balabit import segment_by_clicks
         events = [
             self._make_event(0, "Move", 10, 20),
             self._make_event(100, "Pressed", 50, 50, button="Right"),  # ignored
@@ -164,7 +164,7 @@ class TestSegmentByClicks:
         assert segments[0].click_x == 70
 
     def test_no_clicks_returns_empty(self):
-        from ai_mouse.data_adapters.balabit import segment_by_clicks
+        from tools.data_adapters.balabit import segment_by_clicks
         events = [
             self._make_event(0, "Move", 10, 20),
             self._make_event(100, "Move", 20, 30),
@@ -174,7 +174,7 @@ class TestSegmentByClicks:
 
     def test_excludes_drag_events(self):
         """Drag events are not Move; segment should only include Move."""
-        from ai_mouse.data_adapters.balabit import segment_by_clicks
+        from tools.data_adapters.balabit import segment_by_clicks
         events = [
             self._make_event(0, "Move", 10, 20),
             self._make_event(100, "Drag", 30, 40),       # not Move
@@ -191,7 +191,7 @@ class TestSegmentByClicks:
 class TestFilterSegments:
     def _seg(self, events_data: list[tuple[int, int, int]], click=(500, 500), session="s"):
         """events_data: list of (t_ms, x, y) tuples."""
-        from ai_mouse.data_adapters.balabit import MouseEvent, Segment
+        from tools.data_adapters.balabit import MouseEvent, Segment
         events = [MouseEvent(t_ms=t, button="NoButton", state="Move", x=x, y=y)
                   for (t, x, y) in events_data]
         click_t = events[-1].t_ms + 50 if events else 100
@@ -199,14 +199,14 @@ class TestFilterSegments:
                        click_t_ms=click_t, session_id=session)
 
     def test_drops_segment_with_too_few_events(self):
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         seg = self._seg([(0, 100, 100), (50, 105, 105)])  # 2 events, min=5
         result = filter_segments([seg], min_events=5, min_dist=10,
                                   max_span_ms=5000, max_gap_ms=200)
         assert result == []
 
     def test_drops_segment_with_short_distance(self):
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         # Start (100,100), end click=(105,100) → dist=5, min_dist=50
         events = [(i*10, 100+i, 100) for i in range(10)]
         seg = self._seg(events, click=(105, 100))
@@ -215,7 +215,7 @@ class TestFilterSegments:
         assert result == []
 
     def test_drops_segment_with_too_long_span(self):
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         # Span 6000ms, max_span=5000
         events = [(0, 100, 100), (2000, 200, 200), (4000, 300, 300), (6000, 400, 400),
                   (6010, 410, 400), (6020, 420, 400)]
@@ -225,7 +225,7 @@ class TestFilterSegments:
         assert result == []
 
     def test_drops_segment_with_gap(self):
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         # Gap of 500ms between events 2 and 3, max_gap=200
         events = [(0, 100, 100), (50, 110, 110), (100, 120, 120),
                   (600, 200, 200), (650, 210, 210), (700, 220, 220)]
@@ -235,7 +235,7 @@ class TestFilterSegments:
         assert result == []
 
     def test_drops_segment_with_out_of_range_coords(self):
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         # x=10000 out of range
         events = [(i*10, 10000, 100) for i in range(6)]
         seg = self._seg(events, click=(10100, 100))
@@ -245,7 +245,7 @@ class TestFilterSegments:
 
     def test_drops_segment_with_short_arc_length(self):
         """Total arc < 50 even though endpoints are far → high-frequency jitter only."""
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         # Tiny back-and-forth with click 100px away — unrealistic, drop it
         events = [(i*10, 100 + (i % 2), 100) for i in range(10)]
         seg = self._seg(events, click=(200, 100))
@@ -255,7 +255,7 @@ class TestFilterSegments:
         assert result == []
 
     def test_keeps_valid_segment(self):
-        from ai_mouse.data_adapters.balabit import filter_segments
+        from tools.data_adapters.balabit import filter_segments
         # Smooth 100→500 px straight line, 10 events, span 500ms
         events = [(i*50, 100 + i*40, 100) for i in range(10)]
         seg = self._seg(events, click=(500, 100))
@@ -267,7 +267,7 @@ class TestFilterSegments:
 class TestProcessSession:
     def test_writes_jsonl_in_expected_format(self, tmp_path):
         from tools.config import BalabitAdapterConfig
-        from ai_mouse.data_adapters.balabit import process_session
+        from tools.data_adapters.balabit import process_session
 
         # Construct a Balabit-format CSV with one valid segment
         csv_path = tmp_path / "user_session_42"
@@ -304,7 +304,7 @@ class TestProcessSession:
 
     def test_returns_zero_for_session_with_no_valid_segments(self, tmp_path):
         from tools.config import BalabitAdapterConfig
-        from ai_mouse.data_adapters.balabit import process_session
+        from tools.data_adapters.balabit import process_session
 
         csv_path = tmp_path / "empty_session"
         _write_csv(csv_path, ["0,0.000,NoButton,Move,100,100"])  # no clicks
@@ -319,7 +319,7 @@ class TestProcessSession:
 
     def test_appends_to_existing_jsonl(self, tmp_path):
         from tools.config import BalabitAdapterConfig
-        from ai_mouse.data_adapters.balabit import process_session
+        from tools.data_adapters.balabit import process_session
 
         out = tmp_path / "out.jsonl"
         out.write_text('{"meta":{"start":[0,0],"end":[1,1]},"events":[]}\n', encoding="utf-8")
diff --git a/tests/test_eval_metrics.py b/tests/test_eval_metrics.py
index 2083447..55bd9c3 100644
--- a/tests/test_eval_metrics.py
+++ b/tests/test_eval_metrics.py
@@ -8,7 +8,7 @@ import pytest
 class TestKinematics:
     def test_compute_speed_constant_velocity(self):
         """Constant-velocity trajectory has constant speed."""
-        from ai_mouse.eval.metrics import compute_speed
+        from tools.eval.metrics import compute_speed
         # 10 points, moving 10 px in 100 ms each step → speed = 0.1 px/ms
         xs = np.arange(0, 100, 10, dtype=float)
         ys = np.zeros(10, dtype=float)
@@ -20,7 +20,7 @@ class TestKinematics:
 
     def test_compute_speed_handles_zero_dt(self):
         """Adjacent points with same timestamp must not produce NaN/inf."""
-        from ai_mouse.eval.metrics import compute_speed
+        from tools.eval.metrics import compute_speed
         xs = np.array([0.0, 10.0, 20.0])
         ys = np.array([0.0, 0.0, 0.0])
         ts = np.array([0.0, 0.0, 100.0])  # zero dt between [0] and [1]
@@ -29,7 +29,7 @@ class TestKinematics:
 
     def test_compute_acceleration(self):
         """Linearly increasing speed → constant acceleration."""
-        from ai_mouse.eval.metrics import compute_acceleration
+        from tools.eval.metrics import compute_acceleration
         # speeds: 0.1, 0.2, 0.3, 0.4 over dt = 100 ms each → a = 0.001 px/ms²
         speeds = np.array([0.1, 0.2, 0.3, 0.4])
         ts = np.array([100.0, 200.0, 300.0, 400.0])
@@ -37,7 +37,7 @@ class TestKinematics:
         np.testing.assert_allclose(a, 0.001, rtol=1e-4)
 
     def test_compute_jerk(self):
-        from ai_mouse.eval.metrics import compute_jerk
+        from tools.eval.metrics import compute_jerk
         # accelerations: 0.001, 0.002, 0.003 over dt = 100 ms → j = 0.00001
         accels = np.array([0.001, 0.002, 0.003])
         ts = np.array([200.0, 300.0, 400.0])
@@ -47,7 +47,7 @@ class TestKinematics:
 
 class TestStatsSummary:
     def test_compute_stats_returns_expected_keys(self):
-        from ai_mouse.eval.metrics import compute_stats
+        from tools.eval.metrics import compute_stats
         x = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
         s = compute_stats(x)
         assert "mean" in s
@@ -59,7 +59,7 @@ class TestStatsSummary:
         assert "p95" in s
 
     def test_cv_for_constant_is_zero(self):
-        from ai_mouse.eval.metrics import compute_stats
+        from tools.eval.metrics import compute_stats
         x = np.full(10, 3.0)
         s = compute_stats(x)
         assert s["cv"] == 0.0
@@ -68,7 +68,7 @@ class TestStatsSummary:
 class TestFftSpectrum:
     def test_finds_dominant_frequency(self):
         """A pure 8 Hz signal should have its peak near 8 Hz."""
-        from ai_mouse.eval.metrics import fft_spectrum
+        from tools.eval.metrics import fft_spectrum
         # Sample at 100 Hz for 1 second
         sample_rate_hz = 100.0
         ts_ms = np.arange(0, 1000, 1000 / sample_rate_hz)
@@ -78,7 +78,7 @@ class TestFftSpectrum:
         assert abs(peak_freq - 8.0) < 1.0  # within 1 Hz
 
     def test_returns_only_positive_frequencies(self):
-        from ai_mouse.eval.metrics import fft_spectrum
+        from tools.eval.metrics import fft_spectrum
         signal = np.random.randn(64)
         freqs, mags = fft_spectrum(signal, 50.0)
         assert (freqs >= 0).all()
@@ -88,7 +88,7 @@ class TestFftSpectrum:
 class TestKlDivergence:
     def test_identical_distributions_zero_kl(self):
         """KL(p, p) ≈ 0."""
-        from ai_mouse.eval.metrics import kl_divergence_histograms
+        from tools.eval.metrics import kl_divergence_histograms
         rng = np.random.default_rng(42)
         x = rng.normal(0, 1, 5000)
         y = rng.normal(0, 1, 5000)
@@ -97,7 +97,7 @@ class TestKlDivergence:
 
     def test_different_distributions_positive_kl(self):
         """Different means → positive KL."""
-        from ai_mouse.eval.metrics import kl_divergence_histograms
+        from tools.eval.metrics import kl_divergence_histograms
         rng = np.random.default_rng(42)
         x = rng.normal(0, 1, 5000)
         y = rng.normal(3, 1, 5000)
@@ -106,7 +106,7 @@ class TestKlDivergence:
 
     def test_handles_disjoint_supports(self):
         """No NaN even when histograms have non-overlapping bins."""
-        from ai_mouse.eval.metrics import kl_divergence_histograms
+        from tools.eval.metrics import kl_divergence_histograms
         x = np.array([1.0, 1.1, 1.2, 1.3, 1.4])
         y = np.array([10.0, 10.1, 10.2, 10.3, 10.4])
         kl = kl_divergence_histograms(x, y, bins=10)
@@ -116,7 +116,7 @@ class TestKlDivergence:
 class TestReportGeneration:
     def test_generates_report_md(self, tmp_path):
         """Smoke test: build_report writes an MD file with all expected sections."""
-        from ai_mouse.eval.report import build_report
+        from tools.eval.report import build_report
 
         # Synthetic generated traces (3 traces, 50 points each)
         rng = np.random.default_rng(0)
diff --git a/ai_mouse/data_adapters/__init__.py b/tools/data_adapters/__init__.py
similarity index 100%
rename from ai_mouse/data_adapters/__init__.py
rename to tools/data_adapters/__init__.py
diff --git a/ai_mouse/data_adapters/__main__.py b/tools/data_adapters/__main__.py
similarity index 86%
rename from ai_mouse/data_adapters/__main__.py
rename to tools/data_adapters/__main__.py
index bb368bd..db63e3e 100644
--- a/ai_mouse/data_adapters/__main__.py
+++ b/tools/data_adapters/__main__.py
@@ -7,7 +7,7 @@ from __future__ import annotations
 
 import sys
 
-from ai_mouse.data_adapters.balabit import main
+from tools.data_adapters.balabit import main
 
 if __name__ == "__main__":
     sys.exit(main())
diff --git a/ai_mouse/data_adapters/balabit.py b/tools/data_adapters/balabit.py
similarity index 100%
rename from ai_mouse/data_adapters/balabit.py
rename to tools/data_adapters/balabit.py
diff --git a/ai_mouse/eval/__init__.py b/tools/eval/__init__.py
similarity index 100%
rename from ai_mouse/eval/__init__.py
rename to tools/eval/__init__.py
diff --git a/ai_mouse/eval/__main__.py b/tools/eval/__main__.py
similarity index 98%
rename from ai_mouse/eval/__main__.py
rename to tools/eval/__main__.py
index 27ff9cd..c09f99d 100644
--- a/ai_mouse/eval/__main__.py
+++ b/tools/eval/__main__.py
@@ -110,7 +110,7 @@ def main(argv: list[str] | None = None) -> int:
         logger.error("Empty trace sets — aborting")
         return 1
 
-    from ai_mouse.eval.report import build_report
+    from tools.eval.report import build_report
     args.output.parent.mkdir(parents=True, exist_ok=True)
     build_report(
         generated_traces=gen_traces,
diff --git a/ai_mouse/eval/metrics.py b/tools/eval/metrics.py
similarity index 100%
rename from ai_mouse/eval/metrics.py
rename to tools/eval/metrics.py
diff --git a/ai_mouse/eval/report.py b/tools/eval/report.py
similarity index 99%
rename from ai_mouse/eval/report.py
rename to tools/eval/report.py
index 4bbafa7..738d8ec 100644
--- a/ai_mouse/eval/report.py
+++ b/tools/eval/report.py
@@ -15,7 +15,7 @@ import matplotlib
 matplotlib.use("Agg")  # headless
 import matplotlib.pyplot as plt  # noqa: E402
 
-from ai_mouse.eval.metrics import (
+from tools.eval.metrics import (
     compute_acceleration,
     compute_jerk,
     compute_speed,