HF Agent OS — a multi-agent system for managing the full Hugging Face project lifecycle (built with smolagents)

A developer has released HF Agent OS, a multi-agent system built on smolagents that manages the Hugging Face project lifecycle through natural language, including search, inference, upload, and deployment. The system demonstrated autonomous self-correction by recovering from an invalid model ID, and includes a preview-then-confirm safety pattern for write operations. It has been tested against the real Hub with 74 passing unit tests, and the code is available on GitHub.

Hi everyone, I wanted to share a project I’ve been building: HF Agent OS , a small multi-agent platform that lets you search, inspect, run inference on, upload to, and deploy on the Hugging Face Hub — all through natural language. Instead of one monolithic agent trying to do everything, it’s structured as: smolagents.Tool registry shared across all agentsIt’s all built on smolagents , using CodeAgent + InferenceClientModel for each sub-agent. The part I’m most happy with: the Model Agent demonstrated genuine autonomous self-correction during testing. I asked it to run inference on a partial/invalid model ID distilbert-base-uncased-finetuned-sst-2-english , missing the distilbert/ namespace . Instead of just failing, it: list models tool to search the Hub for the correct ID distilbert/distilbert-base-uncased-finetuned-sst-2-english No human intervention — it just recovered on its own. On safety: any tool that can create or modify real Hub resources repo creation, file upload, Space deployment follows a strict preview-then-confirm pattern. A read-only preview tool always shows what would happen target repo, file size, resulting URL before the corresponding write tool is allowed to act, and the write tool only fires on an explicit, unambiguous user request. Everything’s been tested against the real Hub — real repo creation, real file uploads, real inference calls — plus 74 passing unit tests with all Hub calls mocked. One fun constraint I ran into: deploying a real Gradio Space requires a PRO subscription for compute-backed Spaces Static Spaces are free — good reminder that “deployment agent” work also means understanding the platform’s actual billing model, not just the API surface. Code is on GitHub: GitHub - mebrouktalbi76-eng/hf-agent-os · GitHub https://github.com/mebrouktalbi76-eng/hf-agent-os Would love feedback, especially from anyone who’s built multi-agent systems with smolagents — curious how others have approached the planner/routing layer, and whether there’s appetite for something like this as a reusable pattern for other Hub-adjacent workflows.