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
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python ≥3.10 for full functionality; base install is wheels-only but GPU inference and advanced features need optional compiled extras.
- Low install friction with a wheels-only base package.
- Active maintenance with a release 1 day old.
License · maintenance · safety
(unclear) — 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.
last release 2026-08-13 (1 days) · last repo commit 2026-08-05
0 known vulnerabilities (OSV.dev, 2026-08-14) · 83,942 downloads/mo, #14,039 on PyPI
Alternatives
Verify before relying
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"- 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.
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 on this page. Verify before relying on it.
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
abstract-hugpy-dev on PyPI
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.
Requires Python ≥3.10 for full functionality; base install is wheels-only but GPU inference and advanced features need optional compiled extras.
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"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 | Not declared unclear |
| Python support | Supports the current Python release >=3.6 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 16 packagesabstract-searchflaskgunicornwaitresshttpxaiohttprequestsabstract_essentialsplatformdirshuggingface_hubbeautifulsoup4PyPDF2pdfplumberabstract_apisabstract_flaskabstract_queries |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 83,942 / month, #14,039 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: Other/Proprietary License |
Evidence: abstract_hugpy_dev-0.1.233-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “self-hosted llm api server”
- abstract-hugpy-devA self-hosted LLM console and OpenAI-compatible API server that runs…
- litellm-enterpriseLiteLLM Enterprise provides a unified Python SDK and self-hosted AI…
- aegra-apiAegra API is a self-hosted Agent Protocol server that runs AI agent…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also ipex-llm · llama-cpp-python · open-webui · llama-index-llms-openai-like · llama-index-llms-openai · langchain-huggingface · llm · ogx_open_client · vllm · gguf