anneal-memory

v0.7.1 suspicious
5.0
Medium Risk

Living memory for AI agents. Episodes compress into identity.

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits a moderate risk level due to its use of obfuscation techniques and the maintainer's incomplete profile. While there are no direct indications of malicious activity, the potential for hidden functionality warrants further scrutiny.

  • High obfuscation risk
  • Incomplete maintainer profile
Per-check LLM notes
  • Network: No network calls detected.
  • Shell: Shell execution appears to be part of the package's intended functionality, possibly for CLI operations.
  • Obfuscation: The code uses obfuscation techniques such as custom hashing and pickling which may be used to hide functionality or logic.
  • Credentials: No clear signs of credential harvesting are present in the provided code snippets.
  • Metadata: The maintainer has an incomplete profile and a new account, which raises some suspicion but does not strongly indicate malicious intent.

📦 Package Quality Overall: Medium (5.2/10)

✦ High Test Suite 9.0

Test suite present — 14 test file(s) found

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

Some documentation present

  • Detailed PyPI description (61613 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 5.0

Partial type annotation coverage

  • 266 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 5.0

Limited contributor diversity

  • 1 unique contributor(s) across 100 commits in phillipclapham/anneal-memory
  • Single author but highly active (100 commits)

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

⚠ Code Obfuscation score 10.0

Found 6 obfuscation pattern(s)

  • w13_hash = "sha256:" + __import__("hashlib").sha256( entry_w13.encode("utf-8") ).hex
  • ctivation_mode, today=__import__("datetime").date(2026, 6, 6), ) (row,) = store.active() ass
  • 0:00:00Z") restored = pickle.loads(pickle.dumps(err)) assert isinstance(restored, WrapI
  • ) restored = pickle.loads(pickle.dumps(err)) assert isinstance(restored, Store
  • ntinuity") restored = pickle.loads(pickle.dumps(err)) assert restored.path is None
  • mutated",) restored = pickle.loads(pickle.dumps(err)) assert str(restored) == "mutated"
⚠ Shell / Subprocess Execution score 10.0

Found 6 shell execution pattern(s)

  • bprocess.""" result = subprocess.run( [sys.executable, "-m", "anneal_memory.cli", "--
  • # Init result = subprocess.run( [sys.executable, "-m", "anneal_memory.cli", "--
  • # Status result = subprocess.run( [sys.executable, "-m", "anneal_memory.cli", "--
  • .db") # Init subprocess.run( [sys.executable, "-m", "anneal_memory.cli", "--
  • # Record result = subprocess.run( [ sys.executable, "-m", "anneal
  • # Search result = subprocess.run( [ sys.executable, "-m", "anneal
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: claphamdigital.com>

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository phillipclapham/anneal-memory appears legitimate

⚠ Maintainer History score 4.0

2 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" 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 anneal-memory 
Design and develop a conversational AI agent named 'EchoMind' that leverages the 'anneal-memory' package to maintain a dynamic and evolving identity through interactions. This AI should have the ability to remember past conversations and adapt its responses based on historical context while also allowing for episodes of interaction to compress into its evolving identity. Here are the key steps and features for building this application:

1. **Setup Environment**: Ensure your development environment is set up with Python and the 'anneal-memory' package installed.
2. **Core Functionality**: Implement a basic conversational AI framework that can take user inputs and generate relevant outputs.
3. **Memory Integration**: Utilize 'anneal-memory' to manage the AI's memory, ensuring it can store, retrieve, and update information from past interactions. This includes setting up functions for adding new memories, retrieving relevant memories based on current context, and compressing older memories as new ones are added.
4. **Contextual Adaptation**: Develop logic within EchoMind that allows it to adapt its responses based on the context of the conversation and its evolving identity.
5. **User Interface**: Create a simple text-based interface or integrate with popular chat platforms like Discord or Slack for a more interactive experience.
6. **Testing and Refinement**: Test EchoMind extensively with various scenarios to ensure it behaves as expected and refine its responses and memory management based on feedback.
7. **Deployment**: Once satisfied with EchoMind's performance, deploy it to a server where it can interact with users continuously.

Suggested Features:
- **Dynamic Personality Shifts**: Allow EchoMind to change its personality traits over time based on the type of interactions it has.
- **Emotional Response System**: Implement a system where EchoMind can respond with different emotions based on the tone of the conversation.
- **Learning from User Feedback**: Enable EchoMind to learn and adjust its behavior based on explicit feedback from users about its responses.
- **Security Measures**: Implement security measures to protect user data and ensure privacy.

By following these steps and implementing these features, you'll create a unique conversational AI that not only remembers but also evolves through interactions.