--- id: abstract-hugpy-dev version: "0.1.233" license: hugpy — Source-Available License Copyright (c) 2026 putkoff (hugpy.ai). All rights reserved. Permission is granted, free of charge, to use this software ("hugpy") for personal and non-commercial… (full text in the JSON record) license_treatment: unclear maintenance: active --- # abstract-hugpy-dev — Self-hosted LLM console: model registry & downloads, streaming chat, OpenAI-compatible /v1 API with on-site keys, GPU worker fleet with cross-machine RPC sharding License: unclear · Maintenance: active · Downloads: 83.9K/mo ## What it is and what it does abstract_hugpy_dev is a development distribution of hugpy, a self-hosted LLM platform that combines a web console, model registry, and OpenAI-compatible API in a single Python process. It lets you run local language models and expose them through a `/v1` API endpoint compatible with standard LLM clients. The package ships with a built-in browser UI for model management and chat, eliminating the need for separate frontend builds or reverse proxies. The system is designed for operational self-hosting: it handles model downloads, streaming inference, on-site API key management, and optional GPU worker coordination across multiple machines. The base install is lightweight and wheels-only so it runs on constrained environments; heavy features like inference engines, vision, OCR, and web scraping are opt-in extras that lazy-load only when used. It supports distributed inference by splitting large models across multiple GPUs via RPC sharding, and includes a Discord bot arm for chat integration. Use it for: - Run a local LLM API that any OpenAI-compatible client can call without external hosting or API keys. - Build a multi-GPU inference cluster by joining worker machines to a central coordinator over HTTP. - Serve a web console and API from a single hugpy serve command on a development machine or small server. - Evaluate commercial LLM use cases for thirty (30) days free before committing to a production license. - Integrate local model inference into a Discord bot or other chat application via the built-in bot arm. - Lazy-load heavy dependencies only for workloads that need them. ## Worth the install? AI-flagged interpretation of the facts above — verify before relying. A self-hosted LLM console and OpenAI-compatible API server that runs model inference, chat, and a web UI in a single process, with support for GPU worker fleets and cross-machine model sharding. Yes, with conditions. Install if you need a self-hosted LLM API with an integrated web console and are comfortable with the source-available license (non-commercial free, thirty (30) day commercial trial, then licensing required). The low install friction, active maintenance, and zero known vulnerabilities are strong signals. Verify that the license terms align with your use case—personal and non-profit use is clear, but commercial production deployment requires a license agreement. ## Install pip install abstract-hugpy-dev uv add abstract-hugpy-dev poetry add abstract-hugpy-dev ## Installing abstract-hugpy-dev Before you install: Low install friction with a wheels-only base package. Active maintenance with a release 1 day old. Sixteen runtime dependencies including flask, gunicorn, httpx, and model-serving libraries; optional extras add heavier compiled dependencies on demand. License in practice: Source-available license with non-commercial and personal use permitted free; commercial use requires a license from the copyright holder after a thirty (30) day evaluation period. Redistribution is prohibited without permission. Evaluate your intended use carefully against these terms. Quickstart: pip install abstract_hugpy_dev hugpy serve --host 0.0.0.0 --port 7002 # Then access console at http://localhost:7002/ and API at /v1 # Drive the API with any OpenAI-compatible client # using base_url="http://localhost:7002/v1" and api_key="hp_your_key_here" Requires Python ≥3.10 for full functionality; base install is wheels-only but GPU inference and advanced features need optional compiled extras. Verify before relying: - Whether the thirty (30) day commercial evaluation period is enforced programmatically or on honor system. - Performance characteristics and throughput limits under typical multi-user/multi-model load. - Stability and production-readiness of cross-machine RPC sharding for large models. - Whether the source-available license is compatible with your organization's policies. ## Package facts - License: hugpy — Source-Available License Copyright (c) 2026 putkoff (hugpy.ai). All rights reserved. Permission is granted, free of charge, to use this software ("hugpy") for personal and non-commercial… (full text in the JSON record) (unclear) - Python support: supports_current - Install friction: low - Maintenance: active - Downloads: 83.9K/month (top 15,000 on PyPI) - Known vulnerabilities: none known ## Tags self-hosted llm api server, openai-compatible local inference, llama.cpp console, gpu worker fleet, distributed model serving, local language model deployment, gguf model runner, self-hosted-llm, openai-compatible, gpu-worker-fleet [View on SkillFed](https://skillfed.io/packages/abstract-hugpy-dev) · [View on PyPI](https://pypi.org/project/abstract-hugpy-dev/)