Skip to content
@Neural-alchemy

Neuralchemy

Build secure, reliable, and long-term AI systems focused on safety, reasoning, and developer tooling.
README.md

Neuralchemy

Secure AI systems for long-term reliability.

Research and engineering focused on:

  • AI security
  • Prompt injection defense
  • Reasoning systems
  • Developer infrastructure

We build production-grade tools designed for safety, clarity, and maintainability.

Projects

OpenClay

OpenClay

Secure First → Execute Second

Universal zero-trust execution framework for LLM agents.

Repository: https://github.com/openclay-ai/openclay

Prompt Injection Model

prompt-injection-deberta

Security-focused DeBERTa model for prompt injection detection.

Model: https://huggingface.co/neuralchemy/prompt-injection-deberta

Dataset

Prompt-injection-dataset

  • 6k curated samples
  • 15k augmented samples

Dataset: https://huggingface.co/datasets/neuralchemy/Prompt-injection-dataset

Links

Website: https://www.neuralchemy.in
Hugging Face: https://huggingface.co/neuralchemy
GitHub Org: https://github.com/openclay-ai

Build systems that remain secure under real conditions.

Popular repositories Loading

  1. promptxploit promptxploit Public

    LLM Penetration Testing Framework - Discover vulnerabilities in AI applications before attackers do. 100attacks + AI-powered adaptive mode.

    Python 5 2

  2. Openpentest-labs-web Openpentest-labs-web Public

    OpenPentest is an open-source pentesting lab system where learners exploit real vulnerabilities, understand the engineering constraints behind them, apply the fix, and retest like a pentester to co…

    Python 1

  3. .github .github Public

Repositories

Showing 3 of 3 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…