> For the complete documentation index, see [llms.txt](https://riteshs4hu.gitbook.io/infosec-notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://riteshs4hu.gitbook.io/infosec-notes/artificial-intelligence/ai-agents/ai-and-llm-resources.md).

# AI & LLM Resources

### Paid

* [https://chatgpt.com](https://chatgpt.com/) — Chat-based AI model. CLI version available as **Codex**.
* [https://claude.ai](https://claude.ai/) — Chat-based AI model. CLI version available as **Claude**. Good for coding.
* [https://openrouter.ai](https://openrouter.ai/) — Supports multiple LLMs (ChatGPT, Claude, Gemini, etc.).
* [https://huggingface.co](https://huggingface.co/) — Open-source LLM models.

***

### Free / Limited

#### Local

{% embed url="<https://ollama.com/>" %}

{% embed url="<https://lmstudio.ai/>" %}

* Supports Hugging Face, models:

{% embed url="<https://github.com/mozilla-ai/llamafile>" %}

{% embed url="<https://github.com/janhq/jan>" %}

#### Limited API

{% embed url="<https://huggingface.co/>" %}

{% embed url="<https://console.groq.com/home>" %}

{% embed url="<https://build.nvidia.com/models>" %}

***

### Open-Source AI Agents

Executes one task at a time. Tested with Ollama local models and GPT-4; works well.

{% embed url="<https://github.com/OpenInterpreter/open-interpreter>" %}

***

{% embed url="<https://github.com/kyegomez/OpenMythos>" %}

{% embed url="<https://arcanum-sec.github.io/arc_pi_taxonomy>" %}

* Train Custom LLM Model

{% embed url="<https://unsloth.ai/>" %}

***

#### Self-Hosted AI

{% embed url="<https://pewdiepie-archdaemon.github.io/odysseus/>" %}

{% embed url="<https://github.com/pewdiepie-archdaemon/odysseus>" %}