diff --git a/metagpt/llm.py b/metagpt/llm.py
index e6f815950..8b4a13838 100644
--- a/metagpt/llm.py
+++ b/metagpt/llm.py
@@ -8,6 +8,7 @@
 
 from metagpt.provider.anthropic_api import Claude2 as Claude
 from metagpt.provider.openai_api import OpenAIGPTAPI as LLM
+from metagpt.provider.human_gpt import HumanGPT
 
 DEFAULT_LLM = LLM()
 CLAUDE_LLM = Claude()
diff --git a/metagpt/provider/human_gpt.py b/metagpt/provider/human_gpt.py
new file mode 100644
index 000000000..bc4d6dc6e
--- /dev/null
+++ b/metagpt/provider/human_gpt.py
@@ -0,0 +1,35 @@
+'''
+Filename: MetaGPT/metagpt/provider/human_speaker.py
+Created Date: Wednesday, November 8th 2023, 11:55:46 pm
+Author: garylin2099
+'''
+from typing import Optional
+from metagpt.provider.base_gpt_api import BaseGPTAPI
+from metagpt.logs import logger
+
+class HumanGPT(BaseGPTAPI):
+    """A dummy GPT that actually takes in human input as its response.
+    This enables replacing LLM anywhere in the framework with a human, thus introducing human interaction
+    """
+
+    def ask(self, msg: str) -> str:
+        logger.info("It's your turn, please type in your response. You may also refer to the context below")
+        rsp = input(msg)
+        if rsp in ["exit", "quit"]:
+            exit()
+        return rsp
+
+    async def aask(self, msg: str, system_msgs: Optional[list[str]] = None) -> str:
+        return self.ask(msg)
+
+    def completion(self, messages: list[dict]):
+        """dummy implementation of abstract method in base"""
+        return []
+
+    async def acompletion(self, messages: list[dict]):
+        """dummy implementation of abstract method in base"""
+        return []
+
+    async def acompletion_text(self, messages: list[dict], stream=False) -> str:
+        """dummy implementation of abstract method in base"""
+        return []
diff --git a/metagpt/roles/role.py b/metagpt/roles/role.py
index 0251176f7..fecca0beb 100644
--- a/metagpt/roles/role.py
+++ b/metagpt/roles/role.py
@@ -15,7 +15,7 @@ from pydantic import BaseModel, Field
 # from metagpt.environment import Environment
 from metagpt.config import CONFIG
 from metagpt.actions import Action, ActionOutput
-from metagpt.llm import LLM
+from metagpt.llm import LLM, HumanGPT
 from metagpt.logs import logger
 from metagpt.memory import Memory, LongTermMemory
 from metagpt.schema import Message
@@ -65,6 +65,7 @@ class RoleSetting(BaseModel):
     goal: str
     constraints: str
     desc: str
+    is_human: bool
 
     def __str__(self):
         return f"{self.name}({self.profile})"
@@ -106,9 +107,10 @@ class RoleContext(BaseModel):
 class Role:
     """Role/Agent"""
 
-    def __init__(self, name="", profile="", goal="", constraints="", desc=""):
-        self._llm = LLM()
-        self._setting = RoleSetting(name=name, profile=profile, goal=goal, constraints=constraints, desc=desc)
+    def __init__(self, name="", profile="", goal="", constraints="", desc="", is_human=False):
+        self._llm = LLM() if not is_human else HumanGPT()
+        self._setting = RoleSetting(name=name, profile=profile, goal=goal,
+                                    constraints=constraints, desc=desc, is_human=is_human)
         self._states = []
         self._actions = []
         self._role_id = str(self._setting)
@@ -122,8 +124,11 @@ class Role:
         self._reset()
         for idx, action in enumerate(actions):
             if not isinstance(action, Action):
-                i = action("")
+                i = action("", llm=self._llm)
             else:
+                if self._setting.is_human and not isinstance(action.llm, HumanGPT):
+                    logger.warning(f"is_human attribute does not take effect,"
+                        f"as Role's {str(action)} was initialized using LLM, try passing in Action classes instead of initialized instances")
                 i = action
             i.set_prefix(self._get_prefix(), self.profile)
             self._actions.append(i)