BYOAIK (Bring Your Own AI Key) is a directory of AI tools that run on your own API key.

Tools that accept your Hugging Face API key (35)

Where your key goes

US compelled disclosure
Ownership not established The operating entity has not been established yet.
Who else is in the request path
Amazon Web Services, Inc. Requests to this endpoint pass through Amazon CloudFront (Amazon Web Services, Inc., US), which terminates TLS in front of the API. That means Amazon Web Services, Inc. decrypts the request and can see the Authorization header carrying your key. This is normal infrastructure practice, not a defect, but it is a party in the path that the provider's own documentation does not mention.
Browser apps
Can call this endpoint directly A browser-based app can call this endpoint directly. A CORS preflight from https://www.byoaik.com returned access-control-allow-origin: *.

Tools that support Hugging Face

  • RamaLama: Runs local models inside rootless containers with no network access by default: auto-detects your GPU, needs no key.
  • text-generation-webui: Desktop app for local models with a full web UI: runs offline with zero telemetry and no API key.
  • Hugging Face Chat UI: Open-source SvelteKit chat interface powering HuggingChat, self-hostable against any OpenAI-compatible endpoint with your own API key.
  • LocalAI: Self-hosted drop-in replacement for the OpenAI API covering text, vision, audio and images: your hardware, no key.
  • vLLM: High-throughput self-hosted serving engine for open models on your own GPUs, behind an OpenAI-compatible API you own.
  • smolagents: Hugging Face's deliberately small agent library, model-agnostic and local-friendly.
  • PocketPal AI: iOS and Android app running GGUF models fully on-device: chat offline with no key and no subscription.
  • Khoj: Open-source, self-hostable AI second brain that chats with your documents and the web.
  • Buzz: Cross-platform desktop app to transcribe and translate audio offline with Whisper, or via your own OpenAI-compatible API key.
  • ChainForge: Visual prompt-engineering environment for comparing prompts across models, with keys you enter or load locally.
  • Guidance: Constrained prompt-programming library for steering model output structure, authenticated with your own key.
  • txtai: Embeddings database that runs models locally by default, with cloud providers optional.
  • Jupyter AI: Generative AI inside JupyterLab, the notebook most teaching and research actually happens in.
  • llm.nvim: Neovim ghost-text completion pointed at whatever endpoint you choose, including your own.
  • GPT Researcher: Autonomous agent that runs deep multi-source web research and writes cited reports using your own LLM provider.
  • Text Generator: Template-driven AI text generation inside your Obsidian notes, using your own provider API keys.
  • prompttools: Python library for experimenting with and unit-testing prompts, executed locally on your own keys.
  • Jan: Open-source local-first desktop AI assistant that runs models offline or via your own cloud provider keys.
  • BeeAI Framework: Open-source framework for building production-ready multi-agent systems in Python and TypeScript with a unified, bring-your-own-key LLM backend.
  • Crush: Glamourous terminal-native agentic coding agent that works with any LLM via your own API key.
  • LlamaIndex: Leading open-source data and agent framework for building research agents; you supply every provider's API key.
  • Text Generator (Obsidian): Bring-your-own-key AI text generation inside Obsidian via templated prompts.
  • CodeCompanion.nvim: AI coding assistant for Neovim, Vim style
  • Tabby: Self-hosted, open-source AI coding assistant (Copilot alternative) you point at the models and providers you choose.
  • Pi: Minimal open-source AI agent toolkit and coding-agent CLI with a unified multi-provider LLM API, BYOK.
  • CrewAI: Open-source Python framework for orchestrating collaborative, role-playing autonomous AI agents.
  • bolt.diy: Open-source in-browser full-stack app builder that runs on any LLM you wire up with your own key.
  • Haystack: Open-source Python framework for building production RAG pipelines and agent workflows with any LLM provider.
  • RAGFlow: Open-source RAG engine with deep document understanding for grounded, cited document Q&A.
  • OpenCode: Open-source, provider-agnostic AI coding agent built for the terminal.
  • Cline: Open-source autonomous coding agent for VS Code, JetBrains, and CLI with bring-your-own-key model support.
  • Witsy: BYOK desktop AI assistant and universal MCP client spanning chat, image, video, voice, and search
  • TypingMind: One-time-purchase power-user chat UI that wraps your own LLM provider keys.
  • Flowise: Open-source drag-and-drop builder for LLM apps and AI agents.
  • Page Assist: Open-source browser extension giving a sidebar and web UI for local and cloud AI models via your own keys.