# fmaclen/hollama

A minimal LLM chat app that runs entirely in your browser

Repository: https://github.com/fmaclen/hollama
Canonical: https://ross.abutalabs.com/products/hollama
Homepage: https://hollama.fernando.is
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, chatbot, local-ai, ollama, llm
Last push: 2025-10-12T02:14:55+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 46, release rhythm 51, longevity 72
- inputs: {"age_days": 1012, "days_push": 326, "days_rel": 326, "gap_med": 3.0, "n_releases_24m": 43}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1179, forks 90 (observed 2026-08-28T04:03:53.440525+00:00)

## What it is
Hollama is a minimal LLM chat application that runs entirely in the browser, connecting to Ollama and OpenAI servers with all data stored locally. It supports text and vision models, reasoning models, markdown rendering, and can be used as a web demo, desktop app, or self-hosted via Docker.

## Use cases
- chat with local ollama models in the browser
- privacy-focused llm chat without accounts
- self-host a minimal chatgpt alternative
- chat with openai api from a local web app
- download and manage ollama models from a ui
- use vision and reasoning models with a simple chat interface

## When to choose
- you want a lightweight, no-signup chat UI for Ollama or OpenAI
- you need all chat history stored locally in the browser
- you want a self-hostable or desktop LLM chat app with minimal setup

## When to avoid
- you need multi-user accounts, team features, or server-side history
- you need RAG pipelines, agent workflows, or tool calling
- you require enterprise features like SSO or audit logging

## Facets
- artifact type: application
- maturity: active
- function: chatbot, chat-interface, llm-inference, markdown, self-hosted
- domain: large-language-models, chatbots, artificial-intelligence, self-hosted, web-development
- platform: browser, windows, self-hosted
- tags: ollama, openai, local-ai, svelte, privacy-first, no-backend, web-server, macos, linux, docker

## Member repositories
- fmaclen/hollama (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:53.440525+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:25:34.366967+00:00, confidence not recorded.
  - readme: https://github.com/fmaclen/hollama (fetched 2026-08-28T04:03:53.440525+00:00, sha e0ff0e03d87f)
- Data as of 2026-08-30T08:39:29.467469+00:00.