llms.py：轻量自托管 ChatGPT 替代方案，支持 530+ 模型与 24 家提供商
Show HN: Llms.py – Lightweight, self-hosted ChatGPT alternative to OpenWebUI
llms.py 发布 v4，定位为轻量、自托管、多用户的 ChatGPT 与 OpenWebUI 替代方案，仅依赖 1 个 Python 库（aiohttp）。它通过单一网关接入 24 家提供商的 530+ 模型，覆盖文本、图像、音频三种模态，并新增扩展系统、Gemini File Search RAG、Agent Profiles、MCP 与 Skills 支持。
llms.py
Open Source lightweight self-hosted, multi-user ChatGPT + OpenRouter + OpenWebUI alternative fortext, image & audio from Local and Cloud LLMs
October 6, 2026 - v4 Released! →
Choose your desktop operating system to see the downloads.
A complete AI Assistant inside your App, using your existing users
530+
Models
24
Providers
3
Modalities · Text · Image · Audio
100%
Open Source & Self-Hosted
1
Python Dependency
(aiohttp)
One tool, every modality
Generate Anything
From a single self-hosted gateway - chat with 530+ models, create images, and synthesize speech across 24 providers
Image Generation Create images via Gemini, OpenAI, OpenRouter, Chutes, Z.ai & Nvidia - right inside the chat and gallery workflow Audio & Speech High-quality text-to-speech with Gemini & OpenRouter models, plus voice-to-text input via the microphone
Create → Publish → Showcase
Your Creations, in the Public Gallery
Anything you generate in llms.py can be published with one click - landing in the live showcase at ai.llmspy.org, browsable by everyone with categories, tags, ratings and infinite scroll.
- Browse generated images & audio by category and tag
- Play full Projects built by AI - games and apps, ready to run
- Free & anonymous publisher account - no email required
Playable & self-contained
Projects Built by AI
Complete, self-contained apps & games - generated with llms.py and published for anyone to open and play
💬 Simple Chat
Ask questions directly from the command line
What's New
Latest release focused on extensibility, expanded provider support, and enhanced user experience
Powered by models.dev integration with automatic daily updates
Extensions System Add features, providers, and customize the UI with flexible plugins Gemini File Search RAG workflows with document stores, categories, and contextual chat Credentials Auth Username/Password authentication with Admin UI and CLI user management Agent Profiles Specialized AI agents with custom prompts, tools, themes, and Planner→Coder workflows Projects Secure workspace isolation that restricts AI agent filesystem access to designated project folders PDF Studio Design pixel-identical PDFs using Typst templates, real-time live preview, schema-driven forms, and AI assistance Tool Support First-class Python function calling for LLM interactions with your environment Server Tools Built-in support for provider hosted Anthropic & OpenRouter server tools like web search MCP Support Connect to Model Context Protocol servers for extended tool capabilities Skills Support Extend AI capabilities with specialized knowledge, workflows, and tools Themes Customize the look and feel with built-in themes or create your own Calculator & Run Code UIs Beautiful UIs to evaluate math and execute Python, JS, TS & C# code Media Gallery Browse and manage all your generated images and audio in one place Voice Input Voice-to-text transcription via microphone button or ALT+D keyboard shortcut Image Generation Built-in support for Gemini, OpenAI, OpenRouter, Chutes, Z.ai and Nvidia Audio Generation TTS support for Gemini 2.5 Flash/Pro Preview models KaTeX Math Rendering Beautiful LaTeX math typesetting for equations and formulas
Model Selector
Smart search, advanced filtering, sorting, and favorites over 530 models from 24 providers
Credentials Auth
Built-in Username/Password authentication with a Sign In page, Admin Web UI and CLI for user managing accounts, roles, and account locking
Agent Profiles & Projects
Configure specialized AI agents with custom prompts, tools, and themes - and scope their filesystem access to secure project workspaces
PDF Studio
Design pixel-identical PDFs using Typst templates, real-time live preview, schema-driven forms, typed code generation, and AI assistance
Gemini-powered knowledge, from source to answer
Turn your content into a trusted AI Assistant
Ingest files, repositories, and websites into managed Gemini File Stores. Curate the exact knowledge each answer can use, verify every citation, then publish a beautiful support Assistant anywhere with one script tag.
One workspace for documents, imports, and Assistants
Curate every source
Upload files and ZIPs, sync folders, or crawl websites into inspectable Markdown before indexing.
Retrieve precisely
Scope Gemini by category, type, status, locale, product, version, tags, or a single document.
Publish with confidence
Ship a branded, citation-backed Website Assistant and review real customer conversations.
Ready to ground Gemini in your own knowledge?
Install the extension, create a File Store, and ask your first citation-backed question.
Tools & Function Calling
First-class Python function calling for LLM interactions
Server Tools
Built-in support for provider-hosted OpenRouter & Anthropic server tools like web search, web fetch & code execution
MCP Support
Extend LLM capabilities with Model Context Protocol servers
Skills Support
Extend AI capabilities with specialized knowledge, workflows, and tools
Calculator UI
Beautiful interface for evaluating Python math expressions
Run Code UI
Execute Python, JavaScript, TypeScript, and C# code with syntax highlighting
KaTeX Math Typesetting
Beautiful rendering of LaTeX math expressions
System Prompts Library
200+ curated system prompts for every use case
Runtime Provider Management
Enable or disable providers on the fly without configuration changes
Ready to Get Started?
Install llms.py and start chatting with 530+ AI models in minutes
来源：Hacker News · llmspy.org