Back to directory

ENZO

A self-hosted AI workspace that chats with more than 300 models across nine providers using your own API keys, with injectable agent skills and self-drafting agents, and no ENZO account or subscription.

ENZO

ENZO is a self-hosted AI workspace. It runs in Docker and connects the browser directly to the AI provider you choose, such as OpenRouter, Google AI Studio, NVIDIA NIM, Groq, Hugging Face, Cloudflare or Gemini, using your own API key, so you pay the provider's normal price with nothing in between.

It catalogs more than 300 models across nine providers with live health checks, bundles 74 injectable agent skills that the agent loop pulls in per run, and includes a two-pass builder that turns a plain-language task description into an operating manual for a new agent. Provider keys are stored in an encrypted, passphrase-protected vault in the browser, with a downloadable recovery file. On a fresh instance, the first validated key claims the instance and unlocks server-side features such as agents, skills and memory.

It is written in TypeScript, ships as a Docker container, and its continuous-integration pipeline includes a security penetration test on every push.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.