arymandeshwal commited on
Commit
a288b15
ยท
1 Parent(s): 2df4758
Files changed (1) hide show
  1. README.md +119 -0
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Project Memory - MCP-Powered Team Memory System
3
+ emoji: ๐Ÿง 
4
+ colorFrom: blue
5
+ colorTo: purple
6
+ sdk: docker
7
+ app_port: 7860
8
+ pinned: false
9
+ license: mit
10
+ short_description: AI-powered shared memory for development teams using MCP
11
+ tags:
12
+ - building-mcp-track-enterprise
13
+ ---
14
+
15
+ # ProjectMemory - MCP 1st Birthday Hackathon Submission
16
+
17
+ Check out the Hackathon details at: https://huggingface.co/MCP-1st-Birthday
18
+
19
+
20
+ ## ๐ŸŽฏ Track 1: Building MCP - Enterprise Category
21
+
22
+ **Project Memory** is a multi-user, multi-project AI memory system powered by MCP (Model Context Protocol). It creates shared project memory where every action gets logged and becomes searchable via semantic search and AI chat.
23
+
24
+ ## ๐Ÿš€ What We Built
25
+
26
+ An MCP server that extends LLM capabilities for enterprise teams by:
27
+ - **Persistent Project Memory**: Every task completion generates AI documentation that becomes searchable knowledge
28
+ - **Semantic Search**: Vector-based memory retrieval across all project activities
29
+ - **MCP Tool Integration**: Exposes project management capabilities as MCP tools
30
+ - **Multi-User Collaboration**: Teams can share and search collective knowledge
31
+
32
+ ## ๐Ÿ› ๏ธ MCP Tools Exposed
33
+
34
+ Our MCP server provides these tools:
35
+ - `create_project`: Initialize a new project workspace
36
+ - `list_projects`: View all available projects
37
+ - `join_project`: Join an existing project
38
+ - `list_tasks`: Get project tasks with status
39
+ - `complete_task`: Mark task as done with AI-generated documentation
40
+ - `memory_search`: Semantic search across project history
41
+ - `list_activity`: View project activity feed
42
+
43
+ ## ๐Ÿ“น Demo Video
44
+
45
+ [Watch our 3-minute demo showing MCP integration with Claude Desktop](#) *(link to be added)*
46
+
47
+ ## ๐Ÿ—๏ธ Architecture
48
+
49
+ ```
50
+ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
51
+ โ”‚ Web Frontend โ”‚โ”€โ”€โ”€โ”€โ–ถโ”‚ FastAPI Backend โ”‚
52
+ โ”‚ (React) โ”‚ โ”‚ (MCP Client) โ”‚
53
+ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
54
+ โ”‚
55
+ โ–ผ
56
+ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
57
+ โ”‚ MCP Server โ”‚
58
+ โ”‚ (TypeScript) โ”‚
59
+ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
60
+ โ”‚
61
+ โ–ผ
62
+ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
63
+ โ”‚ SQLite + Vec โ”‚
64
+ โ”‚ (Embeddings) โ”‚
65
+ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
66
+ ```
67
+
68
+ ## ๐Ÿ’ก Key Features
69
+
70
+ 1. **Task Completion Pipeline**: Transforms user work into searchable documentation
71
+ 2. **Vector Search**: Semantic retrieval using sqlite-vec embeddings
72
+ 3. **Chat Interface**: Natural language queries using MCP tools
73
+ 4. **Activity Feed**: Real-time project activity tracking
74
+ 5. **Multi-Project Support**: Manage multiple projects with isolated memory
75
+
76
+ ## ๐Ÿ”ง Technical Stack
77
+
78
+ - **MCP Server**: TypeScript with @modelcontextprotocol/sdk
79
+ - **Backend**: FastAPI (Python) as MCP client
80
+ - **Frontend**: React + Vite + Tailwind CSS
81
+ - **Database**: SQLite with sqlite-vec for embeddings
82
+ - **AI**: Google Generative AI (Gemini) for documentation generation
83
+ - **Deployment**: Docker container for Hugging Face Spaces
84
+
85
+ ## ๐ŸŽฎ How to Use
86
+
87
+ 1. **Create or Join a Project**: Start by creating a new project or joining an existing one
88
+ 2. **Complete Tasks**: Mark tasks as done and provide context about your work
89
+ 3. **AI Documentation**: System automatically generates searchable documentation
90
+ 4. **Search Memory**: Use semantic search to find any past work or decision
91
+ 5. **Chat with Memory**: Ask questions about project history using natural language
92
+
93
+ ## ๐Ÿšข Deployment
94
+
95
+ This Space runs as a Docker container combining:
96
+ - FastAPI backend serving as MCP client
97
+ - React frontend for user interface
98
+ - MCP server handling all tool operations
99
+ - SQLite database with vector search capabilities
100
+
101
+ ## ๐Ÿ” Environment Variables
102
+
103
+ Configure in Space settings:
104
+ - `GOOGLE_API_KEY`: For Gemini AI integration
105
+ - `DATABASE_URL`: (Optional) Custom database connection
106
+
107
+ ## ๐Ÿ‘ฅ Team
108
+
109
+ *Add team member names here*
110
+
111
+ ## ๐Ÿ“ License
112
+
113
+ MIT License - See LICENSE file for details
114
+
115
+ ## ๐Ÿ”— Links
116
+
117
+ - [GitHub Repository](https://github.com/YOUR_USERNAME/project-memory)
118
+ - [MCP Documentation](https://modelcontextprotocol.io)
119
+ - [Hackathon Page](https://huggingface.co/MCP-1st-Birthday)