feat: add hybrid workspace context provider with RAG and MCP server

README.md

@@ -158,6 +158,7 @@ innovation-lab-examples/
 |---------|-------------|------------|------------|
 | [contributors/community_agent](contributors/community_agent/) | AI community growth agent for events and hackathons | Python, uAgents, ASI:One, Tavily | 🟡 Intermediate |
 | [contributors/news-summarizer-agent](contributors/news-summarizer-agent/) | Fetches top headlines for a topic via NewsAPI and summarizes them with ASI:One, via Chat Protocol | Python, uAgents, NewsAPI, ASI:One | 🟡 Intermediate |
+| contributors/workspace-context-provider | Hybrid AI workspace context provider that indexes local codebases and exposes them through a Streamlit RAG interface and an MCP server for IDE integration | Python, Streamlit, FastMCP, ChromaDB, Sentence Transformers, Watchdog, ASI API | 🟡 Intermediate |
 
 ### 🌐 Web3 & Blockchain
 

contributors/CHANGELOG.md

@@ -12,3 +12,4 @@ Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 - `contributors/` folder and contribution guide for community agent examples
 - `contributors/community_agent/` — moved from repository root; AI community growth agent for events and hackathons
 - `contributors/news-summarizer-agent/` — beginner-friendly agent that fetches top headlines via NewsAPI and summarizes them with ASI:One; now a uAgent with Chat Protocol support
+- `contributors/workspace-context-provider/` : Hybrid AI workspace context provider that indexes local codebases and exposes them through a Streamlit RAG interface and an MCP server for IDE integration

contributors/workspace-context-provider/README.md

@@ -0,0 +1,232 @@
+# Autonomous Workspace Context Provider
+
+A hybrid AI context provider that continuously indexes your local workspace and exposes it through a Streamlit web interface and an MCP server for AI-powered code understanding.
+
+---
+
+# 1. Overview
+
+The **Autonomous Workspace Context Provider** is a local Retrieval-Augmented Generation (RAG) agent that monitors your workspace, embeds your source code and documentation into a persistent vector database, and provides contextual information through two interfaces:
+
+* **Streamlit Web UI** for chatting with your codebase using the **ASI**** LLM API**
+* **Model Context Protocol (MCP) Server** for integrating your local RAG pipeline with AI coding assistants such as VS Code (Cline/Roo Code), cursor, claude Desktop etc.
+
+### Category
+
+MCP, RAG, Tooling, Frontend
+
+### Tech Stack
+
+* Python
+* Streamlit
+* FastMCP
+* ChromaDB
+* Sentence Transformers
+* Watchdog
+* ASI API
+
+
+---
+
+# 2. Features
+
+* 🔄 Real-time workspace indexing using **watchdog**
+* 🧠 Local embeddings with **all-MiniLM-L6-v2**
+* 💾 Persistent vector storage using **ChromaDB**
+* 🤖 Chat with your codebase through **ASI**
+* 🔌 MCP server for IDE integration 
+* ⚡ Automatic vector database updates whenever files change
+
+---
+
+# 3. Prerequisites
+
+* Python 3.10+
+* pip
+* ASI API Key *(optional, required only for Streamlit chat)*
+
+---
+
+# 4. Installation
+
+```bash
+cd contributors/workspace-context-provider
+
+python -m venv venv
+
+# Windows
+venv\Scripts\activate
+
+# macOS/Linux
+source venv/bin/activate
+
+pip install -r requirements.txt
+```
+
+---
+
+# 5. Environment Variables
+
+Create a `.env` file.
+
+```bash
+cp .env.example .env
+```
+
+Example `.env.example`
+
+```env
+# Required only for Streamlit AI chat
+ASI1_API_KEY=your_asi1_api_key_here
+
+# Local directory to monitor and index
+WORKSPACE_DIR=./target_workspace
+```
+
+### Variables
+
+| Variable        | Description                                                       |
+| --------------- | ----------------------------------------------------------------- |
+| `ASI1_API_KEY`  | Optional. Used for ASI LLM requests in the Streamlit application. |
+| `WORKSPACE_DIR` | Directory that will be monitored and indexed into ChromaDB.       |
+
+---
+
+# 6. Run the Agent
+
+## Streamlit Web UI
+
+```bash
+streamlit run app.py
+```
+
+The application will automatically begin monitoring the directory specified by `WORKSPACE_DIR`.
+
+---
+
+## MCP Server
+
+Configure your IDE (Cline/Roo Code) by adding the following configuration to `cline_mcp_settings.json`.
+
+```json
+{
+  "mcpServers": {
+    "workspace-rag-provider": {
+      "command": "C:/path/to/venv/Scripts/python.exe",
+      "args": ["-m", "src.mcp_server"],
+      "cwd": "C:/path/to/contributors/workspace-context-provider",
+      "env": {
+        "WORKSPACE_DIR": "./target_workspace"
+      }
+    }
+  }
+}
+```
+
+> **Note:** Replace the `command` and `cwd` values with the absolute paths on your machine.
+
+---
+
+# 7. Expected Output
+
+After running the project:
+
+* ✅ Workspace monitoring starts successfully
+* ✅ Modified files are automatically indexed
+* ✅ Embeddings are stored in ChromaDB
+* ✅ Streamlit UI answers questions about your codebase
+* ✅ MCP server connects successfully to your IDE
+* ✅ AI assistants can retrieve relevant workspace context
+
+---
+
+# 8. Demo
+
+Add screenshots or GIFs demonstrating the project.
+
+```markdown
+![Workspace Context Provider Demo](./assets/demo.png)
+```
+
+---
+
+
+
+# 9. Architecture
+
+```
+               Workspace Files
+                      │
+                      ▼
+              Watchdog Observer
+                      │
+              File Change Events
+                      │
+                      ▼
+        Sentence Transformer Embeddings
+          (all-MiniLM-L6-v2 Model)
+                      │
+                      ▼
+                 ChromaDB
+          (Persistent Vector Store)
+              ▲                 ▲
+              │                 │
+              │                 │
+      Streamlit UI         FastMCP Server
+              │                 │
+              ▼                 ▼
+        ASI:One API      VS Code / Cursor / claude desktop
+```
+
+---
+
+# 10. Troubleshooting
+
+### Missing `ASI1_API_KEY`
+
+If using the Streamlit chat interface, ensure the API key is present in your `.env` file.
+
+---
+
+### Workspace not being indexed
+
+* Verify that `WORKSPACE_DIR` exists.
+* Ensure the application has permission to access the directory.
+
+---
+
+### MCP server not connecting
+
+* Check the absolute paths in `cline_mcp_settings.json`.
+* Restart your IDE after updating the MCP configuration.
+
+---
+
+### Dependency issues
+
+Recreate the virtual environment and reinstall dependencies.
+
+```bash
+rm -rf venv
+
+python -m venv venv
+
+pip install -r requirements.txt
+```
+
+---
+
+# 12. License
+
+This project follows the license of the parent repository unless stated otherwise.
+
+---
+
+# ✅ Quick Checklist Before PR
+
+* [x] README updated using the repository template
+* [x] `.env.example` added
+* [ ] Demo image/GIF added under `assets/`
+* [ ] Agent profile link included (if available)
+* [ ] `ruff check .` passed
+* [ ] `ruff format .` applied

contributors/workspace-context-provider/app.py

@@ -0,0 +1,117 @@
+import streamlit as st
+from openai import OpenAI
+import os
+from dotenv import load_dotenv
+from src.rag_pipeline import LocalRagEngine
+from src.watcher import start_directory_watcher
+
+# Load environment variables
+load_dotenv()
+ASI1_API_KEY = os.getenv("ASI1_API_KEY", "")
+WORKSPACE_DIR = os.getenv("WORKSPACE_DIR", "./target_workspace")
+
+
+# ==========================================
+# 1. INITIALIZE RAG & WATCHER (Cached)
+# ==========================================
+@st.cache_resource
+def init_rag_system():
+    """Initializes the vector DB and background watcher only once per session."""
+    engine = LocalRagEngine()
+    # Start the background file watcher thread
+    start_directory_watcher(engine, WORKSPACE_DIR)
+    return engine
+
+
+rag_engine = init_rag_system()
+
+# ==========================================
+# 2. INITIALIZE ASI:ONE API CLIENT
+# ==========================================
+# ASI:One uses OpenAI-compatible endpoints.
+client = OpenAI(
+    api_key=ASI1_API_KEY,
+    base_url="https://api.asi1.ai/v1",  # Standard ASI:One endpoint
+)
+
+# ==========================================
+# 3. STREAMLIT UI SETUP
+# ==========================================
+st.set_page_config(page_title="Workspace Context Agent", page_icon="🤖", layout="wide")
+st.title("🤖 Autonomous Workspace Agent")
+st.markdown("*Powered by ASI:One & Local RAG*")
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat history
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# ==========================================
+# 4. CHAT LOGIC & RAG INJECTION
+# ==========================================
+if prompt := st.chat_input("Ask about your codebase... (e.g., 'How does auth work?')"):
+    # Display user prompt
+    with st.chat_message("user"):
+        st.markdown(prompt)
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    # Fetch context from our local RAG pipeline
+    with st.spinner("🔍 Scanning local workspace..."):
+        local_context = rag_engine.query_context(prompt, top_k=3)
+
+    # Construct the grounded prompt for ASI:One
+    system_prompt = f"""
+    You are an expert developer AI assistant. 
+    Use the following retrieved local workspace context to answer the user's question accurately.
+    If the answer isn't in the context, say so.
+
+    LOCAL WORKSPACE CONTEXT:
+    {local_context}
+    """
+
+    # Display assistant response
+    with st.chat_message("assistant"):
+        message_placeholder = st.empty()
+
+        if not ASI1_API_KEY:
+            st.error(
+                "⚠️ ASI1_API_KEY is missing in your .env file! Displaying retrieved raw context instead:"
+            )
+            message_placeholder.code(local_context)
+            st.session_state.messages.append(
+                {
+                    "role": "assistant",
+                    "content": f"**Raw Context Retrieved:**\n```\n{local_context}\n```",
+                }
+            )
+        else:
+            try:
+                # Call ASI:One API
+                stream = client.chat.completions.create(
+                    model="asi1-mini",  # Replace with specific ASI1 model if needed
+                    messages=[
+                        {"role": "system", "content": system_prompt},
+                        {"role": "user", "content": prompt},
+                    ],
+                    stream=True,
+                )
+
+                full_response = ""
+                for chunk in stream:
+                    # SAFETY CHECK: Ensure choices list is not empty!
+                    if chunk.choices and len(chunk.choices) > 0:
+                        if chunk.choices[0].delta.content is not None:
+                            full_response += chunk.choices[0].delta.content
+                            message_placeholder.markdown(full_response + "▌")
+
+                message_placeholder.markdown(full_response)
+                st.session_state.messages.append(
+                    {"role": "assistant", "content": full_response}
+                )
+
+            except Exception as e:
+                st.error(f"API Error: {e}")

contributors/workspace-context-provider/requirements.txt

@@ -0,0 +1,7 @@
+uagents
+chromadb 
+sentence-transformers 
+langchain-text-splitters
+watchdog
+streamlit
+openai