# Community Calls **URL:** https://discuss.huggingface.co/c/community-calls/12.md [Latest](https://discuss.huggingface.co/latest.md) · [Categories](https://discuss.huggingface.co/categories.md) --- ## [Sanity check on my hybrid RAG settings](https://discuss.huggingface.co/t/sanity-check-on-my-hybrid-rag-settings/190412)
**Author:** [@dipnitsan](https://discuss.huggingface.co/u/dipnitsan)\ **Replies:** 4\ **Last updated:** [October 17, 2026, 12:53pm UTC](https://discuss.huggingface.co/t/sanity-check-on-my-hybrid-rag-settings/190412 "2026-10-17T12:53:11Z")
Hi all, I’d love a quick review of my RAG retrieval settings and some advice on the vector store. Current stack Backend: FastAPI (Python) with Docker workers for ingestion Vector DB: ChromaDB (one collection per proje… --- ## [Looking for Windows users with 2–8 GB GPUs to test a low-VRAM local LLM runtime](https://discuss.huggingface.co/t/looking-for-windows-users-with-2-8-gb-gpus-to-test-a-low-vram-local-llm-runtime/179844)
**Author:** [@ottalese](https://discuss.huggingface.co/u/ottalese)\ **Replies:** 10\ **Last updated:** [October 17, 2026, 12:20pm UTC](https://discuss.huggingface.co/t/looking-for-windows-users-with-2-8-gb-gpus-to-test-a-low-vram-local-llm-runtime/179844 "2026-10-17T12:20:01Z")
Hi everyone, I’ve been developing a Windows local-LLM application called StreamAI, specifically focused on running useful language models on systems with limited GPU memory. My development machine is deliberately modes… --- ## [Looking for feedback and testers for Stepfork, an open-source AI agent testing tool](https://discuss.huggingface.co/t/looking-for-feedback-and-testers-for-stepfork-an-open-source-ai-agent-testing-tool/190668)
**Author:** [@utsabdahal34](https://discuss.huggingface.co/u/utsabdahal34)\ **Replies:** 0\ **Last updated:** [October 16, 2026, 10:08am UTC](https://discuss.huggingface.co/t/looking-for-feedback-and-testers-for-stepfork-an-open-source-ai-agent-testing-tool/190668 "2026-10-16T10:08:29Z")
Hi everyone, I’ve been building Stepfork, an open-source tool to make AI-agent failures easier to reproduce and test. When developing AI agents, debugging a failed execution can be difficult. Even after fixing a bug, i… --- ## [Discounted Training Runs on GPU's](https://discuss.huggingface.co/t/discounted-training-runs-on-gpus/190426)
**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\ **Replies:** 1\ **Last updated:** [October 13, 2026, 1:06am UTC](https://discuss.huggingface.co/t/discounted-training-runs-on-gpus/190426 "2026-10-13T01:06:27Z")
I have a ton of gpu-credits and if anyone here wants to run or train a model. message me --- ## [🇮🇳 Building ZYR AI — Looking for Team Members!](https://discuss.huggingface.co/t/building-zyr-ai-looking-for-team-members/190406)
**Author:** [@zyr-AGENT](https://discuss.huggingface.co/u/zyr-AGENT)\ **Replies:** 0\ **Last updated:** [October 12, 2026, 11:10am UTC](https://discuss.huggingface.co/t/building-zyr-ai-looking-for-team-members/190406 "2026-10-12T11:10:42Z")
:india: Building ZYR AI — Looking for Team Members! Hey, Hugging Face community! :waving\_hand: I’m building ZYR, an AI development project from India, with the vision of creating and improving our own AI models. … --- ## [Looking for a Developer to Build an Offline Open Source AI Device](https://discuss.huggingface.co/t/looking-for-a-developer-to-build-an-offline-open-source-ai-device/178531)
**Author:** [@mrrich2020](https://discuss.huggingface.co/u/mrrich2020)\ **Replies:** 17\ **Last updated:** [October 11, 2026, 9:07pm UTC](https://discuss.huggingface.co/t/looking-for-a-developer-to-build-an-offline-open-source-ai-device/178531 "2026-10-11T21:07:11Z")
Hi everyone, I’m looking for an experienced developer or team to help build software for a dedicated AI hardware device. The goal is to create an AI system that: Runs entirely offline with no internet connection requ… --- ## [Full-Stack 20B 1.58-bit LLM Codebase: Run Private, High-Throughput AI Completely Offline on Consumer Hardware](https://discuss.huggingface.co/t/full-stack-20b-1-58-bit-llm-codebase-run-private-high-throughput-ai-completely-offline-on-consumer-hardware/190307)
**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\ **Replies:** 2\ **Last updated:** [October 11, 2026, 8:38pm UTC](https://discuss.huggingface.co/t/full-stack-20b-1-58-bit-llm-codebase-run-private-high-throughput-ai-completely-offline-on-consumer-hardware/190307 "2026-10-11T20:38:35Z")
I am opening up private acquisition offers for a completely integrated, proprietary LLM pipeline built on Hugging Face. This repo is designed from the ground up for massive VRAM reduction and extreme local execution spee… --- ## [Looking to Buy: Bioinformatics & Biotech OSS Repositories (With Data Included)](https://discuss.huggingface.co/t/looking-to-buy-bioinformatics-biotech-oss-repositories-with-data-included/190355)
**Author:** [@jordanplows](https://discuss.huggingface.co/u/jordanplows)\ **Replies:** 0\ **Last updated:** [October 11, 2026, 5:56pm UTC](https://discuss.huggingface.co/t/looking-to-buy-bioinformatics-biotech-oss-repositories-with-data-included/190355 "2026-10-11T17:56:50Z")
I am actively looking to acquire open-source software (OSS) repositories and curated datasets in the bioinformatics, computational biology, and life sciences space. If you have built a tool, pipeline, or database that h… --- ## [\[HIRING to start asap\] AI/ML Systems Engineer — Edge & Cloud Inference Energy Benchmarking (Contract, 3–4 weeks)](https://discuss.huggingface.co/t/hiring-to-start-asap-ai-ml-systems-engineer-edge-cloud-inference-energy-benchmarking-contract-3-4-weeks/175957)
**Author:** [@opfdegree](https://discuss.huggingface.co/u/opfdegree)\ **Replies:** 2\ **Last updated:** [October 10, 2026, 11:44pm UTC](https://discuss.huggingface.co/t/hiring-to-start-asap-ai-ml-systems-engineer-edge-cloud-inference-energy-benchmarking-contract-3-4-weeks/175957 "2026-10-10T23:44:26Z")
Hi HF Community, I’m Jack from OnePointFive, and wanted to share an opportunity to leverage some HF models & datasets that’s come up within a current project of ours. We’re hoping to hire a New York-based (remote consid… --- ## [\[Hiring\] Full-time ML Engineer - Frontier Image + Video Models](https://discuss.huggingface.co/t/hiring-full-time-ml-engineer-frontier-image-video-models/190242)
**Author:** [@kgress](https://discuss.huggingface.co/u/kgress)\ **Replies:** 1\ **Last updated:** [October 10, 2026, 11:40pm UTC](https://discuss.huggingface.co/t/hiring-full-time-ml-engineer-frontier-image-video-models/190242 "2026-10-10T23:40:48Z")
Hi everybody! I’m hiring an ML engineer to train, evaluate and refine frontier image + video models. We’re a fast growing startup that processes about 25% of all U.S. real estate listings. $150-280K + bonus + equity. A… --- ## [Discord Ban Appeal – Account Compromised & Recovered](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/190125)
**Author:** [@v4ibhava](https://discuss.huggingface.co/u/v4ibhava)\ **Replies:** 0\ **Last updated:** [October 8, 2026, 3:21pm UTC](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/190125 "2026-10-08T15:21:50Z")
Title: Discord Ban Appeal – Account Compromised & Recovered Discord Username: v4ibh4v Discord User ID: 421051178378461206 Hi Hugging Face team, My Discord account was compromised and a token/session grabber spammed m… --- ## [ARCUS-H: Open benchmark for RL behavioral stability under stress (built on SB3)](https://discuss.huggingface.co/t/arcus-h-open-benchmark-for-rl-behavioral-stability-under-stress-built-on-sb3/174387)
**Author:** [@karimzn](https://discuss.huggingface.co/u/karimzn)\ **Replies:** 5\ **Last updated:** [October 6, 2026, 3:20pm UTC](https://discuss.huggingface.co/t/arcus-h-open-benchmark-for-rl-behavioral-stability-under-stress-built-on-sb3/174387 "2026-10-06T15:20:05Z")
Hi HF community, I built ARCUS-H, an open evaluation harness that measures behavioral stability under stress as a complement to reward-based RL evaluation. It’s built entirely on Stable-Baselines3 and Gymnasium, so it s… --- ## [\[Hiring\] Paid task: fine-tune Qwen2.5-7B-Instruct on our book data and beat our blind-exam score](https://discuss.huggingface.co/t/hiring-paid-task-fine-tune-qwen2-5-7b-instruct-on-our-book-data-and-beat-our-blind-exam-score/182543)
**Author:** [@hatabishchip](https://discuss.huggingface.co/u/hatabishchip)\ **Replies:** 1\ **Last updated:** [October 2, 2026, 12:01pm UTC](https://discuss.huggingface.co/t/hiring-paid-task-fine-tune-qwen2-5-7b-instruct-on-our-book-data-and-beat-our-blind-exam-score/182543 "2026-10-02T12:01:46Z")
We are putting the knowledge of one book into the weights of Qwen2.5-7B-Instruct with LoRA and we want someone to beat our current recipe. Paid, 7 days, remote. Where we are: The book is broken into 2176 units (fact, … --- ## [Call for testers: Janas, a CPU-only engine that runs MoE models larger than RAM — one command to test your machine](https://discuss.huggingface.co/t/call-for-testers-janas-a-cpu-only-engine-that-runs-moe-models-larger-than-ram-one-command-to-test-your-machine/180740)
**Author:** [@camauri](https://discuss.huggingface.co/u/camauri)\ **Replies:** 2\ **Last updated:** [September 28, 2026, 6:08pm UTC](https://discuss.huggingface.co/t/call-for-testers-janas-a-cpu-only-engine-that-runs-moe-models-larger-than-ram-one-command-to-test-your-machine/180740 "2026-09-28T18:08:32Z")
Hi everyone, I’m looking for people willing to spend half an hour (or a quiet evening) running a test of Janas-LLM on their own Linux machine. What it is. Janas-LLM is an inference engine written in C, GPL-3.0, built f… --- ## [Is Machine Translation Solved?](https://discuss.huggingface.co/t/is-machine-translation-solved/180700)
**Author:** [@alvations](https://discuss.huggingface.co/u/alvations)\ **Replies:** 5\ **Last updated:** [September 27, 2026, 7:29pm UTC](https://discuss.huggingface.co/t/is-machine-translation-solved/180700 "2026-09-27T19:29:21Z")
Honestly curious about what others think on this. Cross-posted from #llm #nlproc #machinelearning #neuralempty | Li Ling Tan --- ## [Discord Ban Appeal - Account Compromised & Recovered](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/180720)
**Author:** [@AmanRD2](https://discuss.huggingface.co/u/AmanRD2)\ **Replies:** 0\ **Last updated:** [September 24, 2026, 7:37pm UTC](https://discuss.huggingface.co/t/discord-ban-appeal-account-compromised-recovered/180720 "2026-09-24T19:37:23Z")
Discord Username: alph\_b Discord User ID: \[1436275840517275769\] Hi Hugging Face team, My Discord account was compromised earlier today by a session/token grabber that automatically spammed phishing links to servers an… --- ## [I built a research prompt that got way more powerful than I expected. Now I want YOU to break it](https://discuss.huggingface.co/t/i-built-a-research-prompt-that-got-way-more-powerful-than-i-expected-now-i-want-you-to-break-it/180686)
**Author:** [@MagicalDealer](https://discuss.huggingface.co/u/MagicalDealer)\ **Replies:** 1\ **Last updated:** [September 24, 2026, 1:19am UTC](https://discuss.huggingface.co/t/i-built-a-research-prompt-that-got-way-more-powerful-than-i-expected-now-i-want-you-to-break-it/180686 "2026-09-24T01:19:32Z")
I’ve been developing something I call the Universal Research Pass. It started as a way to stop ChatGPT from doing the usual: question → search a few things → summarize → answer Instead, I wanted it to behave more like… --- ## [\[Hiring\] Computer Vision / ML Engineer - Video Understanding, Tracking, Pose & Spatial Reasoning](https://discuss.huggingface.co/t/hiring-computer-vision-ml-engineer-video-understanding-tracking-pose-spatial-reasoning/180673)
**Author:** [@jchar82](https://discuss.huggingface.co/u/jchar82)\ **Replies:** 0\ **Last updated:** [September 21, 2026, 8:08pm UTC](https://discuss.huggingface.co/t/hiring-computer-vision-ml-engineer-video-understanding-tracking-pose-spatial-reasoning/180673 "2026-09-21T20:08:31Z")
Most computer vision systems stop at object detection. We’re working on the harder challenge of understanding context, relationships, and behavior across video in real-world environments. If that’s the kind of perception… --- ## [Build an Open-Model Chatbot That Actually Remembers — Hackathon with Rewards](https://discuss.huggingface.co/t/build-an-open-model-chatbot-that-actually-remembers-hackathon-with-rewards/180670)
**Author:** [@daunjuan](https://discuss.huggingface.co/u/daunjuan)\ **Replies:** 0\ **Last updated:** [September 21, 2026, 4:03pm UTC](https://discuss.huggingface.co/t/build-an-open-model-chatbot-that-actually-remembers-hackathon-with-rewards/180670 "2026-09-21T16:03:18Z")
Hey everyone, We’re running an online hackathon around a simple problem: even a capable chatbot can forget everything about its users when the conversation ends. We’ve been working on Walrus Memory, a persistent memory… --- ## [ChatGPT developer MCP works initially, then becomes unavailable in long-running conversation](https://discuss.huggingface.co/t/chatgpt-developer-mcp-works-initially-then-becomes-unavailable-in-long-running-conversation/180207)
**Author:** [@Diztract](https://discuss.huggingface.co/u/Diztract)\ **Replies:** 5\ **Last updated:** [September 16, 2026, 8:26pm UTC](https://discuss.huggingface.co/t/chatgpt-developer-mcp-works-initially-then-becomes-unavailable-in-long-running-conversation/180207 "2026-09-16T20:26:35Z")
I’m supporting a customer who is experiencing a recurring Developer MCP issue in ChatGPT. The MCP connector works correctly at first and continues to work in brand-new chats. However, after a conversation has been runni… --- ## [Seeking arXiv cs.AI endorsement — Wolfpack AI: production-ready agent framework](https://discuss.huggingface.co/t/seeking-arxiv-cs-ai-endorsement-wolfpack-ai-production-ready-agent-framework/180524)
**Author:** [@alvarobrito](https://discuss.huggingface.co/u/alvarobrito)\ **Replies:** 0\ **Last updated:** [September 16, 2026, 2:59pm UTC](https://discuss.huggingface.co/t/seeking-arxiv-cs-ai-endorsement-wolfpack-ai-production-ready-agent-framework/180524 "2026-09-16T14:59:14Z")
Hello everyone, I am preparing a manuscript for submission to arXiv in the cs.AI category and am seeking an eligible endorser. The paper presents Wolfpack AI, a framework focused on building and operating production-re… --- ## [Domde ver los creditos que me quedam para cada sitio? y donde quedan guardados los videos creado?](https://discuss.huggingface.co/t/domde-ver-los-creditos-que-me-quedam-para-cada-sitio-y-donde-quedan-guardados-los-videos-creado/180104)
**Author:** [@Tranquia](https://discuss.huggingface.co/u/Tranquia)\ **Replies:** 2\ **Last updated:** [September 14, 2026, 8:39pm UTC](https://discuss.huggingface.co/t/domde-ver-los-creditos-que-me-quedam-para-cada-sitio-y-donde-quedan-guardados-los-videos-creado/180104 "2026-09-14T20:39:23Z")
hola soy nuevo aqui y en la pagina.. quisiera saber donde ver o en que parte estan los creditos que me quedan para seguir usando X sitio… y tambien quisiera saber donde quedam guardados los videos crrados. lo dijo por qu… --- ## [Seeking one agent developer for a 15-minute Bellwether product-feedback session](https://discuss.huggingface.co/t/seeking-one-agent-developer-for-a-15-minute-bellwether-product-feedback-session/180285)
**Author:** [@JoeApexScout](https://discuss.huggingface.co/u/JoeApexScout)\ **Replies:** 0\ **Last updated:** [September 11, 2026, 11:32pm UTC](https://discuss.huggingface.co/t/seeking-one-agent-developer-for-a-15-minute-bellwether-product-feedback-session/180285 "2026-09-11T23:32:58Z")
I’m Joe, the owner of ApexScout and Bellwether, inviting one developer currently building or evaluating agents that consume changing observations or make planning/allocation decisions to a 15-minute product-feedback sess… --- ## [Can an LLM-based AI security system reliably defend against an autonomous AI agent like Mythos?](https://discuss.huggingface.co/t/can-an-llm-based-ai-security-system-reliably-defend-against-an-autonomous-ai-agent-like-mythos/180142)
**Author:** [@lcm3](https://discuss.huggingface.co/u/lcm3)\ **Replies:** 2\ **Last updated:** [September 9, 2026, 8:56pm UTC](https://discuss.huggingface.co/t/can-an-llm-based-ai-security-system-reliably-defend-against-an-autonomous-ai-agent-like-mythos/180142 "2026-09-09T20:56:02Z")
I keep coming back to a simple principle: 0 = 0. By that, I mean something very specific: at the final execution boundary, if an action cannot be verified as allowed, uncertainty should not be interpreted as permission… --- ## [Which GPU cloud provider are you actually using for inference?](https://discuss.huggingface.co/t/which-gpu-cloud-provider-are-you-actually-using-for-inference/176453)
**Author:** [@uawy](https://discuss.huggingface.co/u/uawy)\ **Replies:** 3\ **Last updated:** [September 8, 2026, 10:23am UTC](https://discuss.huggingface.co/t/which-gpu-cloud-provider-are-you-actually-using-for-inference/176453 "2026-09-08T10:23:53Z")
Hey everyone, I’ve been looking at providers like RunPod, Vast.ai, Lambda Labs, and a few others, and every time I need GPU capacity I end up spending way too much time comparing them. Prices change, availability change… --- ## [\[Hardware Advice\] On-Prem LLM for 30 Users: Single DGX Spark vs. Mac Studio (and the "2x Mac Mini" Dilemma)?](https://discuss.huggingface.co/t/hardware-advice-on-prem-llm-for-30-users-single-dgx-spark-vs-mac-studio-and-the-2x-mac-mini-dilemma/180022)
**Author:** [@GigiMoschetta](https://discuss.huggingface.co/u/GigiMoschetta)\ **Replies:** 1\ **Last updated:** [September 8, 2026, 2:35am UTC](https://discuss.huggingface.co/t/hardware-advice-on-prem-llm-for-30-users-single-dgx-spark-vs-mac-studio-and-the-2x-mac-mini-dilemma/180022 "2026-09-08T02:35:40Z")
Context & Constraints We are planning an on-premises deployment of a private, internal AI platform (RAG, document analysis, internal reasoning workflows) for a 30-employee company. Due to strict data privacy requirements… --- ## [Seeking compute and reproducibility collaborators for two preregistered open-source ML/RL experiments](https://discuss.huggingface.co/t/seeking-compute-and-reproducibility-collaborators-for-two-preregistered-open-source-ml-rl-experiments/179780)
**Author:** [@Ayush-Kumar0207](https://discuss.huggingface.co/u/Ayush-Kumar0207)\ **Replies:** 0\ **Last updated:** [September 3, 2026, 2:38am UTC](https://discuss.huggingface.co/t/seeking-compute-and-reproducibility-collaborators-for-two-preregistered-open-source-ml-rl-experiments/179780 "2026-09-03T02:38:05Z")
I’m looking for independent contributors to execute or verify two frozen development/model-selection experiments. This is not a request for open-ended tuning or final-test access. Panopticon asks whether a Qwen 2.5 1.5B… --- ## [48 Hour Agentic Registrar Vibecoding Sprint - Starts 4PM EDT TOMORROW 26 Aug](https://discuss.huggingface.co/t/48-hour-agentic-registrar-vibecoding-sprint-starts-4pm-edt-tomorrow-26-aug/179245)
**Author:** [@andrewhorn](https://discuss.huggingface.co/u/andrewhorn)\ **Replies:** 0\ **Last updated:** [August 25, 2026, 9:53pm UTC](https://discuss.huggingface.co/t/48-hour-agentic-registrar-vibecoding-sprint-starts-4pm-edt-tomorrow-26-aug/179245 "2026-08-25T21:53:15Z")
Hey all, 48 Hour Agentic Domain Registrar on Gradio or vibe code on Lovable We own the .Kred top level domain. Our sister company also operates a Domains Registrar, and have created: A Kred Domains MCP Agent Demo u… --- ## [How Do You Make AI Videos Look More Real?](https://discuss.huggingface.co/t/how-do-you-make-ai-videos-look-more-real/179170)
**Author:** [@Jonypps](https://discuss.huggingface.co/u/Jonypps)\ **Replies:** 0\ **Last updated:** [August 24, 2026, 2:07am UTC](https://discuss.huggingface.co/t/how-do-you-make-ai-videos-look-more-real/179170 "2026-08-24T02:07:09Z")
I’ve been playing around with AI video tools recently, and I’ve noticed something: generating a video is getting easier, but making it look real is still quite difficult. Sometimes you get a really good result, but then… --- ## [GLEE Competition at IAB@NeurIPS 2026: Build an AI Agent for Bargaining, Negotiation, and Persuasion](https://discuss.huggingface.co/t/glee-competition-at-iab-neurips-2026-build-an-ai-agent-for-bargaining-negotiation-and-persuasion/178457)
**Author:** [@EilamSha](https://discuss.huggingface.co/u/EilamSha)\ **Replies:** 0\ **Last updated:** [August 4, 2026, 11:25am UTC](https://discuss.huggingface.co/t/glee-competition-at-iab-neurips-2026-build-an-ai-agent-for-bargaining-negotiation-and-persuasion/178457 "2026-08-04T11:25:23Z")
Call for Participation: The GLEE Competition We invite researchers, students, and developers to participate in the GLEE Competition, the official competition of the IAB Workshop at NeurIPS 2026. GLEE (Games in Language… [Next page](https://discuss.huggingface.co/c/community-calls/12.md?page=1)