MoHamdyy commited on
Commit
e101baa
·
1 Parent(s): 4b4b93c

Updated README.md file

Browse files
Files changed (1) hide show
  1. README.md +56 -65
README.md CHANGED
@@ -1,69 +1,60 @@
1
- # ContribNavigator
2
-
3
- ContribNavigator is an AI-assisted tool designed to help developers, especially newcomers, find and begin contributing to open-source projects on GitHub. It streamlines issue discovery and provides an intelligently generated onboarding kit.
4
-
5
- ## Core Features
6
-
7
- * **Targeted Issue Search:** Filters GitHub issues by programming language and user-specified topics (e.g., "python" + "machine-learning"), prioritizing beginner-friendly labels like "good first issue."
8
- * **AI-Powered Issue Suggestion:** Leverages an LLM (OpenAI GPT-4o class) to analyze fetched issues and recommend the most suitable starting point for a beginner, with clear reasoning.
9
- * **Intelligent Onboarding Kit:**
10
- * **AI-Planned Components:** An LLM planner dynamically determines the most relevant sections to include in the kit based on the selected issue.
11
- * **Essential Information:** Direct links to the issue and repository, `git clone` command.
12
- * **Contribution Guidelines Analysis:**
13
- * Link to the project's `CONTRIBUTING.md` (or similar).
14
- * AI-generated summary of key contribution procedures (setup, coding style, PR process).
15
- * **Repository Overview (via Modal):**
16
- * Top-level file and directory listing from a sandboxed `git clone` operation executed on Modal.
17
- * AI-suggested relevant files/folders to investigate for the specific issue.
18
- * **First Steps Checklist:** An interactive checklist in the UI to guide users through their initial contribution actions.
19
- * **Agentic Design:** Built with an agentic architecture where an LLM plans and orchestrates the use of internal "tools" (GitHub API client, Modal repo inspector, LLM analysis functions), aligning with Model Context Protocol (MCP) principles.
20
-
21
- ## Tech Stack
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
 
23
  * **UI:** Gradio
24
- * **Backend & Orchestration:** Python
25
- * **Language Models:** OpenAI API (GPT-4o class)
26
- * **Sandboxed Operations:** Modal (for `git clone`)
27
- * **Data Source:** GitHub API
28
-
29
- ## Local Development Setup
30
-
31
- 1. **Prerequisites:**
32
- * Git
33
- * Python (3.10+)
34
- * Modal Account & CLI (`modal token new`)
35
-
36
- 2. **Clone & Install Dependencies:**
37
- ```bash
38
- git clone https://github.com/YOUR_USERNAME/ContribNavigator.git # Replace with your repo URL
39
- cd ContribNavigator
40
- python -m venv .venv
41
- source .venv/bin/activate # On Windows: .venv\Scripts\activate
42
- pip install -r requirements.txt
43
- ```
44
-
45
- 3. **Environment Variables:**
46
- * Create a `.env` file in the project root (refer to `.env.example` if provided).
47
- * Add your API keys:
48
- ```env
49
- GITHUB_PAT="your_github_pat"
50
- OPENAI_API_KEY="sk-your_openai_key"
51
- # MODAL_TOKEN_ID="mi_..." # Optional for local if `modal token new` was used
52
- # MODAL_TOKEN_SECRET="ms_..." # Optional for local
53
- ```
54
-
55
- 4. **Run the Application:**
56
- ```bash
57
- python app.py
58
- ```
59
-
60
- ## Hackathon Context
61
-
62
- * **Project:** ContribNavigator
63
- * **Event:** Agents & MCP Hackathon
64
- * **Primary Track Submission:** Agentic Demos Track
65
- * *Demonstrates an end-to-end AI agent application using Gradio that assists with open-source contributions through intelligent planning and tool utilization (GitHub API, Modal, LLM analysis), reflecting MCP principles.*
66
 
67
- ## License
68
 
69
- This project is licensed under the MIT License. See the `LICENSE` file for details.
 
 
1
+ ---
2
+ title: ContribNavigator
3
+ emoji: 🧭
4
+ colorFrom: blue
5
+ colorTo: green
6
+ sdk: gradio
7
+ python_version: "3.12"
8
+ sdk_version: "4.29.0" # Example: Use a recent Gradio version, check your requirements or latest stable
9
+ app_file: app.py
10
+ pinned: false
11
+ license: mit
12
+ short_description: "AI copilot for beginner open-source issues & planned kits."
13
+ tags: ["agent", "llm", "openai", "modal", "github", "open-source", "developer-tools", "gradio-agent-hackathon", "mcp-hackathon"]
14
+
15
+
16
+ ## ContribNavigator: Your AI Guide to Open Source Contributions
17
+
18
+ **Find beginner-friendly open-source issues and get an AI-planned onboarding kit to kickstart your contribution!**
19
+
20
+ ContribNavigator is an intelligent agent built with Gradio that simplifies finding and starting your first open-source contribution. It uses AI to suggest relevant issues and dynamically generates a comprehensive onboarding kit.
21
+
22
+ ### How to Use:
23
+
24
+ 1. **Select Programming Language:** Choose your preferred language from the dropdown.
25
+ 2. **Specify Topics (Optional):**
26
+ * Select common topics from the multi-select dropdown.
27
+ * Add any custom, comma-separated topics (slugs or phrases like "web development") in the textbox.
28
+ 3. **Find Issues:** Click "🔍 Find Beginner Issues."
29
+ * The app will display recommended issues and an AI Navigator's Insight suggesting a good starting point.
30
+ 4. **Generate Onboarding Kit:**
31
+ * Select an issue from the "Select an Issue to Generate Kit" dropdown (this appears after issues are found).
32
+ * Click "🛠️ Generate Onboarding Kit."
33
+ * View your personalized kit, which includes:
34
+ * Issue and repository links.
35
+ * `git clone` command.
36
+ * AI-summarized contribution guidelines (if found).
37
+ * A repository file structure overview (from a sandboxed clone via Modal).
38
+ * AI-suggested relevant files to start your investigation.
39
+ * An interactive "First Steps Checklist."
40
+
41
+ ### Key Features & Technologies:
42
+
43
+ * **Smart Issue Discovery:** Filters by language and topics, prioritizing beginner-friendly labels.
44
+ * **AI-Powered Suggestions:** Uses OpenAI (GPT-4o class model) for issue recommendations, contribution guideline summaries, and relevant file suggestions.
45
+ * **Intelligent Onboarding Kit:** Dynamically planned by an LLM to include the most relevant information.
46
+ * **Sandboxed Repo Analysis:** Leverages Modal to securely clone repositories and list files.
47
+ * **Agentic Design:** Built with an agentic architecture where an LLM plans and orchestrates the use of internal "tools," reflecting Model Context Protocol (MCP) principles.
48
+
49
+ ### Technical Stack:
50
 
51
  * **UI:** Gradio
52
+ * **Backend:** Python
53
+ * **LLMs:** OpenAI API
54
+ * **Cloud Functions:** Modal
55
+ * **Data:** GitHub API
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
+ ---
58
 
59
+ This Space is a submission for the **Agents & MCP Hackathon**.
60
+ For more details, local setup instructions, and the full source code, please visit our [GitHub Repository](https://github.com/YOUR_USERNAME/ContribNavigator). <!-- Replace with your GitHub repo URL -->