{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiewy2cjnwq7vybtcjtlvhlwax4cnbqxxvopyy54cinvcg5mctchze",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mkiu7frnh422"
  },
  "path": "/t/anyone-willing-to-collaborate-with-me-on-a-local-first-ai-based-research-assistant/175607#post_1",
  "publishedAt": "2026-04-27T18:19:26.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "https://github.com/venkatram-s/gigabook-lm"
  ],
  "textContent": "> **NOTE TO MODS:** This project involves **llama.cpp** and **downloading GGUF models** from **HuggingFace** , so i think it can be posted here. And, i know this does look like a recruitment post, and i have given some justification, by providing details. And, i hope that you guys would read and understand. Thank You\n\nTL;DR - NotebookLM, but Locally with your OWN AI Model\nGithub Repo - https://github.com/venkatram-s/gigabook-lm\n\n  * **My Working Timezone** : UTC + 05:30 (India )\n\n  * **Stack** : Python 3.12, llama.cpp (it could be potentially expanded further)\n\n  * **Experience Level** : All are welcome\n\n  * **Goal** : To build a local alternative to proprietary third-party AI-based research assistants\n\n  * **Monetization** : **NO,** this is a FOSS project.\n\n\n\n\nHi HF Community, I’m Venkatram, a sophomore.\n\nThe idea is to turn documents into researchable assets that contain as much as information as the original information does, but it’s more reusable.\n\nWell, quite frankly, this is still under a WORK IN PROGRESS, so i’m still figuring on how it can be properly used, and I got to be honest here, i definitely need some help to build this, so if you wish, you are welcome!",
  "title": "Anyone willing to collaborate with me on a local-first AI-based research assistant?"
}