# serge-chat/serge

A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.

Repository: https://github.com/serge-chat/serge
Canonical: https://ross.abutalabs.com/products/serge
Homepage: https://serge.chat
Language: Svelte
License: Apache-2.0
License Family: permissive
Topics: llama, alpaca, docker, fastapi, llamacpp, python, web, svelte, sveltekit, tailwindcss, nginx
Archived: true
Last push: 2025-11-21T08:07:36+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 8, longevity 90
- inputs: {"age_days": 1263, "days_push": 285, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5714, forks 388 (observed 2026-08-28T04:09:28.196631+00:00)

## What it is
Serge is a self-hosted web chat interface for running LLMs locally via llama.cpp, built with a SvelteKit frontend and FastAPI backend. It ships fully dockerized with no API keys or data collection required.

## Use cases
- chat with llama models locally in a browser
- self-hosted chatgpt alternative without api keys
- run alpaca llm on my own server
- private local llm chat interface
- deploy llm chat app with docker
- chat with local models offline

## When to choose
- you want a private, self-hosted chat UI for local llama.cpp models
- you prefer a one-command docker deployment with no API keys
- you want a simple REST API on top of llama.cpp

## When to avoid
- you need multi-user production-grade LLM serving at scale
- you want cloud-hosted models like GPT-4 or Claude
- your machine lacks enough RAM for local model inference

## Facets
- artifact type: application
- maturity: active
- function: chat-interface, llm-inference, self-hosted, api-framework
- domain: large-language-models, chatbots, self-hosted
- platform: self-hosted
- tags: llama.cpp, sveltekit, fastapi, local-llm, chat-ui, docker, web-server

## Member repositories
- serge-chat/serge (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.196631+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 2026-08-29T17:53:29.668095+00:00, confidence not recorded.
  - readme: https://github.com/serge-chat/serge (fetched 2026-08-28T04:09:28.196631+00:00, sha b899f1f096bb)
  - homepage: https://serge.chat (fetched 2026-08-29T08:49:07.419771+00:00, sha 44959d2a37c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.