> For the complete documentation index, see [llms.txt](https://sparkhat-research.gitbook.io/sparkhat-reserch-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sparkhat-research.gitbook.io/sparkhat-reserch-docs/sparkhat-research-portfolio.md).

# spArkHAT Research Portfolio

A public index of research and engineering projects developed around human-gated AI, evidence-aware reasoning, reproducibility, and safety-first automation. Public claims distinguish tested configurations from planned capabilities.

## Projects

* [**AIOA spArkHAT**](https://github.com/luciferprosun/AIOA-spArkHAT) — human-gated AI runtime with approval, evidence, provenance, receipts and replay-safety boundaries. [AIOA Hugging Face demo](https://huggingface.co/spaces/LuciferSun333/AIOA).
* [**spArkSWARM**](https://sparkhat-research.gitbook.io/sparkhat-reserch-docs/sparkswarm-controlled-agent-and-outreach-orchestration) — experimental, separately governed research and outreach orchestration. Unrestricted automatic publishing is **not** a completed or enabled capability.
* [**LSC Research**](https://github.com/luciferprosun/LSC-Research) — open, *unvalidated* research with explicit hypotheses, tests and unresolved claims. [LSC Hugging Face Space](https://huggingface.co/spaces/LuciferSun333/LSC).
* [**EagleEYE D'Arc**](https://github.com/luciferprosun/EagleEYE-DArc-showcase) — private OSINT/cybersecurity research with only a bounded public safety/governance showcase.
* [**Non-Zero CloudOps**](https://github.com/luciferprosun/AIOA-NonZero-CloudOps-Agent) — public historical engineering/hackathon work; relevant concepts are integrated into AIOA.

## Evidence boundaries

AIOA's GOLD24 refers to a local historical endurance report, not an independent certification of today's main branch or a LIVE provider test. [Read the scoped evidence review](https://github.com/luciferprosun/AIOA-spArkHAT/blob/main/docs/launch/GOLD24_LOCAL_EVIDENCE_REVIEW_20261013.md). **Gold72 is planned and not yet completed.**

## Public profiles and demos

* [Main project website](https://sparkhat.eu/)
* [GitHub project portfolio](https://github.com/luciferprosun)
* [Research documentation](https://sparkhat-research.gitbook.io/sparkhat-reserch-docs/)
* [Hugging Face AIOA](https://huggingface.co/spaces/LuciferSun333/AIOA) and [LSC](https://huggingface.co/spaces/LuciferSun333/LSC)
* [Devpost hackathon portfolio](https://devpost.com/tonystarrkarc)
* [Video demos](https://www.youtube.com/channel/UCtmop4uC7HP-rxDqk7FN_cA)
* [LinkedIn](https://www.linkedin.com/in/%C5%82ukasz-%C5%BCuchowski-807160316)

Public descriptions stay scoped to verifiable, presentation-safe materials. External partnerships and submissions require appropriate authorization.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://sparkhat-research.gitbook.io/sparkhat-reserch-docs/sparkhat-research-portfolio.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
