diff --git a/python/spider-py/src/spider_py/core/__init__.py b/python/spider-py/src/spider_py/core/__init__.py
index d417d95e2..26e822ca3 100644
--- a/python/spider-py/src/spider_py/core/__init__.py
+++ b/python/spider-py/src/spider_py/core/__init__.py
@@ -1 +1,32 @@
 """Spider core package."""
+
+from .data import Data, DataId
+from .task import (
+    Task,
+    TaskId,
+    TaskInput,
+    TaskInputData,
+    TaskInputOutput,
+    TaskInputValue,
+    TaskOutput,
+    TaskOutputData,
+    TaskOutputValue,
+    TaskState,
+)
+from .task_graph import TaskGraph
+
+__all__ = [
+    "Data",
+    "DataId",
+    "Task",
+    "TaskGraph",
+    "TaskId",
+    "TaskInput",
+    "TaskInputData",
+    "TaskInputOutput",
+    "TaskInputValue",
+    "TaskOutput",
+    "TaskOutputData",
+    "TaskOutputValue",
+    "TaskState",
+]
diff --git a/python/spider-py/src/spider_py/core/data.py b/python/spider-py/src/spider_py/core/data.py
new file mode 100644
index 000000000..7a0586712
--- /dev/null
+++ b/python/spider-py/src/spider_py/core/data.py
@@ -0,0 +1,14 @@
+"""Data module for Spider."""
+
+from dataclasses import dataclass
+from uuid import UUID
+
+DataId = UUID
+
+
+@dataclass
+class Data:
+    """Represents a data object."""
+
+    id: DataId
+    value: bytes
diff --git a/python/spider-py/src/spider_py/core/task.py b/python/spider-py/src/spider_py/core/task.py
index 855f2a72b..d9c81e68d 100644
--- a/python/spider-py/src/spider_py/core/task.py
+++ b/python/spider-py/src/spider_py/core/task.py
@@ -1,5 +1,50 @@
 """Task module for Spider."""
 
+from dataclasses import dataclass, field
+from enum import IntEnum
+from uuid import UUID, uuid4
 
+from spider_py.core.data import DataId
+
+TaskId = UUID
+
+
+@dataclass
+class TaskInputOutput:
+    """Represents a task input that references the output of another task by its ID and position."""
+
+    task_id: TaskId
+    position: int
+
+
+TaskInputValue = bytes
+TaskInputData = DataId
+TaskInput = TaskInputOutput | TaskInputValue | TaskInputData
+
+TaskOutputValue = bytes
+TaskOutputData = DataId
+TaskOutput = TaskOutputValue | TaskOutputData
+
+
+class TaskState(IntEnum):
+    """Represents the state of a task"""
+
+    Pending = 0
+    Ready = 1
+    Running = 2
+    Succeeded = 3
+    Failed = 4
+    Cancelled = 5
+
+
+@dataclass
 class Task:
     """Represents a task in Spider."""
+
+    task_id: TaskId = field(default_factory=uuid4)
+    function_name: str = ""
+    state: TaskState = TaskState.Pending
+    timeout: float = 0
+    max_retries: int = 0
+    task_inputs: list[TaskInput] = field(default_factory=list)
+    task_outputs: list[TaskOutput] = field(default_factory=list)
diff --git a/python/spider-py/src/spider_py/core/task_graph.py b/python/spider-py/src/spider_py/core/task_graph.py
new file mode 100644
index 000000000..845bbd7c0
--- /dev/null
+++ b/python/spider-py/src/spider_py/core/task_graph.py
@@ -0,0 +1,62 @@
+"""TaskGraph module for Spider."""
+
+from spider_py.core.task import Task, TaskId
+
+
+class TaskGraph:
+    """
+    Represents a task graph in Spider.
+    TaskGraph represents a directed acyclic graph (DAG) of tasks.
+    It stores:
+    - tasks: A dictionary mapping task ids to Task objects.
+    - dependencies: A list of tuples representing the dependencies between tasks. Each tuple
+      contains:
+        - parent task id
+        - child task id
+    - input_tasks: A set of task ids that have no parents (input tasks).
+    - output_tasks: A set of task ids that have no children (output tasks).
+    """
+
+    def __init__(self) -> None:
+        """Initializes an empty task graph."""
+        self.tasks: dict[TaskId, Task] = {}
+        self.dependencies: list[tuple[TaskId, TaskId]] = []
+        self.input_tasks: set[TaskId] = set()
+        self.output_tasks: set[TaskId] = set()
+
+    def add_task(
+        self, task: Task, parents: list[TaskId] | None = None, children: list[TaskId] | None = None
+    ) -> None:
+        """
+        Adds a task to the graph.
+        :param task: The task to add.
+        :param parents: The parent ids of the task. Must be already in the task graph.
+        :param children: The children ids of the task. Must be already in the task graph.
+        """
+        self.tasks[task.task_id] = task
+        if parents is not None and len(parents) > 0:
+            for parent in parents:
+                self.dependencies.append((parent, task.task_id))
+                self.output_tasks.discard(parent)
+        else:
+            self.input_tasks.add(task.task_id)
+        if children is not None and len(children) > 0:
+            for child in children:
+                self.dependencies.append((task.task_id, child))
+                self.input_tasks.discard(child)
+        else:
+            self.output_tasks.add(task.task_id)
+
+    def get_parents(self, task_id: TaskId) -> list[Task]:
+        """
+        :param task_id:
+        :return: Parent tasks of the task identified by `task_id`.
+        """
+        return [self.tasks[parent] for (parent, child) in self.dependencies if child == task_id]
+
+    def get_children(self, task_id: TaskId) -> list[Task]:
+        """
+        :param task_id:
+        :return: Child tasks of the task identified by `task_id`.
+        """
+        return [self.tasks[child] for (parent, child) in self.dependencies if parent == task_id]