Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
title: Forge AI Agent
|
3 |
-
emoji:
|
4 |
colorFrom: blue
|
5 |
colorTo: green
|
6 |
sdk: gradio
|
@@ -8,31 +8,46 @@ sdk_version: 5.36.2
|
|
8 |
python_version: 3.10
|
9 |
app_file: app.py
|
10 |
---
|
|
|
|
|
11 |
|
12 |
-
|
13 |
|
14 |
-
|
|
|
|
|
15 |
|
16 |
-
|
|
|
17 |
|
18 |
-
|
19 |
-
|
20 |
-
3. **Execution**: The Forge orchestrator executes each step in the plan by calling the appropriate tool from a mock MCP server.
|
21 |
-
4. **Live Feedback**: The agent's thoughts, actions, and results are streamed to the UI in real-time.
|
22 |
|
23 |
-
|
|
|
24 |
|
25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
|
27 |
-
1. **Install dependencies:**
|
28 |
-
```bash
|
29 |
-
pip install -r requirements.txt
|
30 |
-
```
|
31 |
-
2. **Run the mock servers in a separate terminal:**
|
32 |
-
```bash
|
33 |
-
python mock_mcp_servers/run_servers.py
|
34 |
-
```
|
35 |
-
3. **Run the Gradio app:**
|
36 |
-
```bash
|
37 |
-
gradio app.py
|
38 |
-
```
|
|
|
1 |
---
|
2 |
title: Forge AI Agent
|
3 |
+
emoji: 🚀
|
4 |
colorFrom: blue
|
5 |
colorTo: green
|
6 |
sdk: gradio
|
|
|
8 |
python_version: 3.10
|
9 |
app_file: app.py
|
10 |
---
|
11 |
+
🧠 Forge: The Autonomous AI Software Engineer
|
12 |
+
Forge is an experimental AI agent that simulates autonomous software development. Given a high-level goal, the agent plans and executes tasks using a suite of tools accessible via the Model Context Protocol (MCP).
|
13 |
|
14 |
+
This demo showcases Forge's architecture and logic, integrated with a mock MCP server and a real-time Gradio interface.
|
15 |
|
16 |
+
🔍 How It Works
|
17 |
+
Define a Goal
|
18 |
+
Enter a high-level software task (e.g., "Build a Flask API for user signup").
|
19 |
|
20 |
+
Planning Phase
|
21 |
+
A mock AI agent analyzes the goal and lists available tools, then generates a step-by-step execution plan.
|
22 |
|
23 |
+
Execution Phase
|
24 |
+
The Forge orchestrator runs each step in the plan by invoking appropriate tools via a mock MCP server.
|
|
|
|
|
25 |
|
26 |
+
Live Agent Feedback
|
27 |
+
The UI streams the agent’s decisions, actions, and intermediate results in real-time.
|
28 |
|
29 |
+
🧪 Local Development
|
30 |
+
To run Forge locally, you'll need to set up both the mock MCP servers and the Gradio interface.
|
31 |
+
|
32 |
+
1. Install Dependencies
|
33 |
+
bash
|
34 |
+
Copy
|
35 |
+
Edit
|
36 |
+
pip install -r requirements.txt
|
37 |
+
2. Start Mock MCP Servers (in a separate terminal)
|
38 |
+
bash
|
39 |
+
Copy
|
40 |
+
Edit
|
41 |
+
python mock_mcp_servers/run_servers.py
|
42 |
+
3. Launch the Gradio App
|
43 |
+
bash
|
44 |
+
Copy
|
45 |
+
Edit
|
46 |
+
python app.py
|
47 |
+
🚧 Notes
|
48 |
+
The current agent logic is mocked for demonstration.
|
49 |
+
|
50 |
+
The system is modular and can be extended to use real tools, LLMs, and dynamic backends.
|
51 |
+
|
52 |
+
This project uses Gradio 5.36.2 and Python 3.10.
|
53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|