diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..39b3736
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,14 @@
+[build-system]
+requires = ["flit_core >=3.2,<4"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "eip_testing"
+authors = [{name = "Nils Pukropp", email = "nils@narl.io"}]
+readme = "README.md"
+license = {file = "LICENSE"}
+classifiers = ["License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)"]
+dynamic = ["version", "description"]
+
+[project.urls]
+Home = "https://github.com/narrrl/eip_testing"
diff --git a/src/__init__.py b/src/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/testing.py b/src/testing.py
new file mode 100644
index 0000000..bd89a94
--- /dev/null
+++ b/src/testing.py
@@ -0,0 +1,119 @@
+import functools
+import multiprocessing
+from typing import Callable, Iterator
+
+
+class TimeoutException(Exception):
+    pass
+
+def get_subtasks_for(cls: type) -> Iterator[type]:
+    """get all tasks in a tasks aka subtasks"""
+    return [e for e in cls.__dict__.values() if hasattr(e, 'is_task')]
+
+
+def get_tests_for(cls: type) -> Iterator[Callable[[], None]]:
+    """get all functions that are declared as tests"""
+    return [e for e in cls.__dict__.values() if hasattr(e, 'is_test')]
+
+def test_wrapper(test: Callable[[], None]):
+    try:
+        test()
+    except Exception as e:
+        test.has_failed = True
+        test.cause = e
+    
+
+def run_test(test: Callable[[], None]):
+    """run a test and catch any unexpected behavior and mark it as failed with the exception as cause"""
+    if not hasattr(test, 'is_test'):
+        return
+    timeout = test.timeout
+    p = multiprocessing.Process(target=test_wrapper, args=[test])
+    p.start()
+    p.join(timeout)
+    if p.is_alive():
+        test.has_failed = True
+        test.cause = TimeoutException(f"test failed after {timeout} seconds")
+
+
+def run_tests_for_task(task: type) -> None:
+    for test in task.tests:
+        run_test(test)
+    for task in task.tasks:
+        run_tests_for_task(task)
+
+
+def points_to_detuct(e: type | Callable) -> int:
+    match e:
+        case type() if hasattr(e, 'is_task'):
+            to_detuct = 0
+            for test in e.tests:
+                if hasattr(test, 'is_test'):
+                    to_detuct += test.to_deduct()
+            for task in e.tasks:
+                to_detuct += points_to_detuct(task)
+            return e.max_points if to_detuct > e.max_points else to_detuct
+        case Callable(test):
+            return test.to_detuct()
+        case _:
+            return 0
+
+
+class Exercise(object):
+    def __init__(self, id: str) -> None:
+        self.__tasks: list[type] = []
+        self.__id = id
+        self.__max_points = 0
+        self.__points = 0
+
+    def register(self, cls: type) -> None:
+        if hasattr(cls, 'is_task'):
+            self.__tasks.append(cls)
+            self.__max_points += cls.max_points
+        return cls
+    
+    def run(self) -> str:
+        self.run_tests()
+        self.deduct_points()
+        
+
+    def run_tests(self):
+        for task in self.__tasks:
+            run_tests_for_task(task)
+
+    def deduct_points(self):
+        for task in self.__tasks:
+            to_detuct = points_to_detuct(task)
+            task.points = 0 if to_detuct > task.max_points else task.max_points - to_detuct
+        self.__points = functools.reduce(
+            lambda a, b: a + b, map(lambda t: t.points, self.__tasks), 0.0)
+
+    def get_points(self) -> float:
+        return self.__points
+
+    def get_max_points(self) -> float:
+        return self.__max_points
+
+
+def eip_task(header: str, max_points: float, ex: Exercise) -> Callable[[type], type]:
+    def wrapper(cls: type) -> type:
+        cls.is_task = True
+        cls.header = header
+        cls.max_points = max_points
+        cls.tasks = get_subtasks_for(cls)
+        cls.tests = get_tests_for(cls)
+        ex.register(cls)
+        return cls
+    return wrapper
+
+
+def eip_test(msg: str, to_deduct: float, timeout = 10) -> Callable[[], None]:
+    def wrapper(test: Callable[[], None]) -> Callable[[], None]:
+        test.is_test = True
+        test.msg = msg
+        test.has_failed = False
+        test.to_deduct = lambda: to_deduct if test.has_failed else 0
+        test.timeout = timeout
+        test.cause = None
+        return test
+    return wrapper
diff --git a/src/tests/primes.py b/src/tests/primes.py
new file mode 100644
index 0000000..1d1e63c
--- /dev/null
+++ b/src/tests/primes.py
@@ -0,0 +1,29 @@
+def is_prime(n: int) -> bool:
+    if n < 2:
+        return False
+
+    for i in range(2, n // 2 + 1):
+        if n % i == 0:
+            return False
+
+    return True
+
+
+def next_prime(n: int) -> int:
+    num = n + 1
+    while not is_prime(num):
+        num += 1
+    return num
+
+def prime_factorize(n: int) -> list[int]:
+    prime_factors: list[int] = []
+    num = n
+    prime = 2
+    while num > 1:
+        if num % prime == 0:
+            prime_factors.append(prime)
+            num //= prime
+            prime = 2
+        else:
+            prime = next_prime(prime)
+    return prime_factors
diff --git a/src/tests/test_testing.py b/src/tests/test_testing.py
new file mode 100644
index 0000000..b175e9c
--- /dev/null
+++ b/src/tests/test_testing.py
@@ -0,0 +1,103 @@
+from utils import has_annotation_callable
+from testing import eip_task, eip_test, Exercise
+
+PRIMES = [2, 3, 5, 7, 11, 13, 17, 19, 23, 29, 31, 37,
+          41, 43, 47, 53, 59, 61, 67, 71, 73, 79, 83, 89, 97]
+PRIME_FACTORS = {2: [2], 3: [3], 4: [2, 2], 5: [5], 6: [2, 3], 7: [7], 8: [2, 2, 2], 9: [3, 3], 10: [2, 5], 11: [11], 12: [2, 2, 3], 13: [13], 14: [2, 7], 15: [3, 5], 16: [2, 2, 2, 2], 17: [17], 18: [2, 3, 3], 19: [19], 20: [2, 2, 5], 21: [3, 7], 22: [2, 11], 23: [23], 24: [2, 2, 2, 3], 25: [5, 5], 26: [2, 13], 27: [3, 3, 3], 28: [2, 2, 7], 29: [29], 30: [2, 3, 5], 31: [31], 32: [2, 2, 2, 2, 2], 33: [3, 11], 34: [2, 17], 35: [5, 7], 36: [2, 2, 3, 3], 37: [37], 38: [2, 19], 39: [3, 13], 40: [2, 2, 2, 5], 41: [41], 42: [2, 3, 7], 43: [43], 44: [2, 2, 11], 45: [3, 3, 5], 46: [2, 23], 47: [47], 48: [2, 2, 2, 2, 3], 49: [7, 7], 50: [2, 5, 5], 51: [3, 17], 52: [2, 2, 13], 53: [53], 54: [
+    2, 3, 3, 3], 55: [5, 11], 56: [2, 2, 2, 7], 57: [3, 19], 58: [2, 29], 59: [59], 60: [2, 2, 3, 5], 61: [61], 62: [2, 31], 63: [3, 3, 7], 64: [2, 2, 2, 2, 2, 2], 65: [5, 13], 66: [2, 3, 11], 67: [67], 68: [2, 2, 17], 69: [3, 23], 70: [2, 5, 7], 71: [71], 72: [2, 2, 2, 3, 3], 73: [73], 74: [2, 37], 75: [3, 5, 5], 76: [2, 2, 19], 77: [7, 11], 78: [2, 3, 13], 79: [79], 80: [2, 2, 2, 2, 5], 81: [3, 3, 3, 3], 82: [2, 41], 83: [83], 84: [2, 2, 3, 7], 85: [5, 17], 86: [2, 43], 87: [3, 29], 88: [2, 2, 2, 11], 89: [89], 90: [2, 3, 3, 5], 91: [7, 13], 92: [2, 2, 23], 93: [3, 31], 94: [2, 47], 95: [5, 19], 96: [2, 2, 2, 2, 2, 3], 97: [97], 98: [2, 7, 7], 99: [3, 3, 11], 100: [2, 2, 5, 5]}
+MAX = 100
+
+
+primes_exercise = Exercise("primes")
+
+
+@eip_task("`is_prime`", 4, primes_exercise)
+class IsPrime:
+
+    @eip_test("`is_prime` nicht implementiert", 4)
+    def is_implemented():
+        from primes import is_prime as _
+
+    @eip_test("Manche Primzahlen evaluieren zu `False`", 2)
+    def test_primes():
+        from primes import is_prime
+        for prime in PRIMES:
+            assert is_prime(prime), f"`is_prime({prime}) = False`"
+
+    @eip_test("Manche Zahlen evaluieren zu `True` obwohl keine Primzahl", 2)
+    def test_non_primes():
+        from primes import is_prime
+        for not_prime in [num for num in range(4, MAX + 1) if num not in PRIMES]:
+            assert not is_prime(not_prime), f"`is_prime({not_prime}) = True`"
+
+    @eip_test("Typeannotation ist nicht korrekt/unvollständig", 0.5)
+    def test_annotation():
+        from primes import is_prime
+        has_annotation_callable(is_prime, [int], bool)
+
+
+@eip_task("`next_prime`", 6, primes_exercise)
+class NextPrime:
+
+    @eip_test("`next_prime` nicht implementiert", 6)
+    def is_implemented():
+        from primes import next_prime as _
+
+    @eip_test("Stimmt nicht für alle überprüften Werte", 4)
+    def test_next_prime():
+        from primes import next_prime
+        for num in range(2, PRIMES[len(PRIMES) - 1]):
+            prime = next_prime(num)
+            i = 0
+            while i < len(PRIMES) - 1 and num >= PRIMES[i + 1]:
+                i += 1
+            p1 = PRIMES[i]
+            p2 = PRIMES[i + 1]
+            assert p1 <= num < p2 and p2 == prime, f"`next_prime({num}) = {prime} != {p2}`"
+
+    @eip_test("`next_prime` evaluiert nicht `2` für Werte kleiner als `2`", 1)
+    def test_lower_values_next_prime():
+        import primes
+        for num in range(-2, 2):
+            assert primes.next_prime(num) == 2, f"`next_prime({num}) != 2`"
+
+    @eip_test("`Typannotation inkorrekt/unvollständig", 0.5)
+    def test_next_prime_annotation():
+        import primes
+        has_annotation_callable(primes.next_prime, [int], int)
+
+
+@eip_task("c) `prime_factorize`", 10, primes_exercise)
+class PrimeFactorize:
+
+    @eip_test("`prime_factorize` nicht implementiert", 10)
+    def prime_factorize_implemented():
+        from primes import prime_factorize as _
+
+    @eip_test("`prime_factorize` gibt nicht immer die korrekten Faktoren", 8)
+    def test_prime_factorize():
+        import primes
+        for prime in PRIMES:
+            assert primes.prime_factorize(prime) == [prime], f"prime_factorize({prime}) = {primes.prime_factorize(prime)} != [{prime}]"
+        prime_factors = [(n, primes.prime_factorize(n))
+                         for n in range(2, MAX + 1)]
+        for n, factors in prime_factors:
+            for factor in factors:
+                assert factor in PRIMES, f"{factor} in {factors} is not prime"
+            assert PRIME_FACTORS[n] == factors, f"prime_factorize({n}) = {factors} != {PRIME_FACTORS[n]}"
+
+    @eip_test("`prime_factorize` gibt keine leere Liste für Werte kleiner 2", 2)
+    def test_lower_values_next_prime():
+        import primes
+        for num in range(-2, 2):
+            assert primes.next_prime(num) == 2
+
+    @eip_test("`Typannotation inkorrekt/unvollständig", 0.5)
+    def test_type_annotation():
+        import primes
+        has_annotation_callable(primes.prime_factorize, [int], list[int])
+
+
+if __name__ == "__main__":
+    primes_exercise.run()
+    print(f"# exercise ({primes_exercise.get_points():.2g} / {primes_exercise.get_max_points()})")
diff --git a/src/utils.py b/src/utils.py
new file mode 100644
index 0000000..705dc56
--- /dev/null
+++ b/src/utils.py
@@ -0,0 +1,14 @@
+from typing import Callable, TypeAliasType
+
+def has_annotation_callable(f: Callable, param_types: list[type], return_type: object = None):
+    a = f.__annotations__
+    ret = a['return'] if 'return' in a else None
+    assert ret == return_type
+
+    params = list(a.values())[:-1] if 'return' in a else list(a.values())
+    for param, param_type in zip(params, param_types):
+        while isinstance(param, TypeAliasType):
+            param = param.__value__
+        while isinstance(param_type, TypeAliasType):
+            param_type = param_type.__value__
+        assert param == param_type
\ No newline at end of file