ai-memory-mcp

v0.7.0 safe
3.0
Low Risk

Python SDK for the ai-memory HTTP API (persistent memory for AI agents).

🤖 AI Analysis

Final verdict: SAFE

The ai-memory-mcp package presents a low risk profile with no detected obfuscation, shell execution, or credential harvesting activities. While there is a moderate network risk due to potential unknown destinations, the lack of other red flags suggests it is likely not a supply-chain attack.

  • No obfuscation, shell execution, or credential harvesting detected.
  • Moderate network risk due to network calls, but no clear evidence of malicious intent.
Per-check LLM notes
  • Network: The package makes network calls which could be for legitimate purposes like API health checks, but further investigation is needed to confirm the destination and purpose.
  • Shell: No shell execution patterns were detected, suggesting no immediate risk from this aspect.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious obfuscation.
  • Credentials: No credential harvesting patterns detected, indicating low risk of secret or credential theft.
  • Metadata: The maintainer has only one package, suggesting a potentially new or less active account, but no other red flags are present.

📦 Package Quality Overall: Medium (5.8/10)

✦ High Test Suite 9.0

Test suite present — 2 test file(s) found

  • Test runner config found: pyproject.toml
  • 2 test file(s) detected (e.g. test_client.py)
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (4497 chars)
○ Low Contributing Guide 2.0

No contributing guide or governance files found

  • No CONTRIBUTING, CODE_OF_CONDUCT, or governance files found
◈ Medium Type Annotations 7.0

Partial type annotation coverage

  • Classifier: Typing :: Typed
  • 70 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 6.0

Limited contributor diversity

  • 2 unique contributor(s) across 100 commits in alphaonedev/ai-memory-mcp
  • Two distinct contributors found

🔬 Heuristic Checks

⚠ Outbound Network Calls score 4.5

Found 3 network call pattern(s)

  • None: self._client = httpx.AsyncClient( **build_httpx_kwargs( base_url=
  • None: self._client = httpx.Client( **build_httpx_kwargs( base_url=
  • e try: response = httpx.get(f"{TEST_BASE_URL}/api/v1/health", timeout=2.0) except ht
✓ Code Obfuscation

No obfuscation patterns detected

✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

No author email provided

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository alphaonedev/ai-memory-mcp appears legitimate

⚠ Maintainer History score 2.0

1 maintainer concern(s) found

  • Author "AlphaOne LLC" appears to have only 1 package on PyPI (new or inactive account)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with ai-memory-mcp 
Develop a personal AI agent assistant that leverages the 'ai-memory-mcp' package to manage its persistent memory. This mini-app will serve as a daily planner and note-taker, capable of remembering user inputs over time without losing data between sessions. Here’s a detailed breakdown of the application's functionality and steps to implement it using the 'ai-memory-mcp' package:

1. **Setup Environment**: Begin by setting up your development environment. Ensure you have Python installed along with the necessary libraries, including 'ai-memory-mcp'. Initialize a new Python project and install the required packages.

2. **Initialize Memory**: Use the 'ai-memory-mcp' package to initialize the memory space for your AI agent. This involves setting up a connection to the ai-memory service and configuring any necessary parameters such as namespace or key-value pairs.

3. **User Interaction**: Design a simple command-line interface where users can interact with their AI assistant. Users should be able to add notes, set reminders, and view past interactions. Each interaction should be stored in the AI agent's memory using the 'ai-memory-mcp' package.

4. **Persistent Storage**: Implement logic to ensure that all user interactions and notes are stored persistently using the 'ai-memory-mcp' package. This means that when the app is closed and reopened, all previously saved data should still be accessible.

5. **Querying Past Interactions**: Allow users to query past interactions by date, keyword, or specific content. The AI agent should be able to retrieve and display these interactions from its memory.

6. **Advanced Features** (Optional): Consider adding advanced features such as natural language processing for more intuitive user input, integration with calendar apps for scheduling reminders, or even voice commands for hands-free operation.

7. **Testing and Debugging**: Thoroughly test the application to ensure that all functionalities work as expected. Pay special attention to the persistence of data across sessions and the accuracy of queries.

8. **Documentation and Deployment**: Document the setup process, usage instructions, and any troubleshooting tips. Optionally, deploy the application on a platform like GitHub for others to use or contribute to.

This project aims to demonstrate the practical application of the 'ai-memory-mcp' package in building a useful, persistent memory-based AI assistant.