# cocktailpeanut/dalai

The simplest way to run LLaMA on your local machine

Repository: https://github.com/cocktailpeanut/dalai
Canonical: https://ross.abutalabs.com/products/dalai
Homepage: https://cocktailpeanut.github.io/dalai
Language: CSS
License Family: other
Topics: ai, llama, llm
Last push: 2024-06-18T20:29:46+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 90
- inputs: {"age_days": 1270, "days_push": 806, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license, no_readme
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12896, forks 1324 (observed 2026-08-28T04:11:00.052269+00:00)

## What it is
Dalai is a self-hosted application that makes it simple to run LLaMA (and Alpaca) language models locally with a one-command installer and a built-in web chat interface. It wraps model serving and a browser UI so non-experts can chat with local LLMs without manual setup.

## Use cases
- run llama on my local machine
- chat with a local llm without the cloud
- self-host llama with a simple web ui
- install alpaca model locally easily
- offline chatbot on my own computer

## When to choose
- you want the simplest possible local LLaMA setup with a ready-made chat UI
- you prefer a one-command install over manual model serving
- you need offline/private LLM inference on a personal machine

## When to avoid
- you need production-grade serving, quantization options, or broad model support
- you want an actively developed tool with current model support
- you need GPU-optimized inference or an OpenAI-compatible API

## Facets
- artifact type: application
- maturity: maintenance
- function: llm-inference, chat-interface, http-server
- domain: large-language-models, artificial-intelligence, self-hosted
- platform: windows, self-hosted
- tags: llama, local-llm, web-ui, one-click-install, macos, linux, nodejs

## Member repositories
- cocktailpeanut/dalai (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:00.052269+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 2026-08-29T17:13:42.239967+00:00, confidence not recorded.
  - homepage: https://cocktailpeanut.github.io/dalai (fetched 2026-08-29T08:09:42.156162+00:00, sha f8711090db16)
- Data as of 2026-08-30T08:39:29.467469+00:00.