# danielgross/localpilot

Repository: https://github.com/danielgross/localpilot
Canonical: https://ross.abutalabs.com/products/localpilot
Language: Python
License: MIT
License Family: permissive
Last push: 2024-02-25T18:19:04+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 76
- inputs: {"age_days": 1067, "days_push": 920, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3348, forks 139 (observed 2026-08-28T04:07:57.697113+00:00)

## What it is
A local proxy server that emulates GitHub Copilot by running open-source code-completion LLMs (via llama.cpp/GGML) on a Mac, so VS Code's Copilot extension can be pointed at it for fully on-device autocomplete. It is a Python app that downloads models and serves completions on localhost.

## Use cases
- run github copilot locally on my mac
- offline code completion without internet
- self-hosted copilot alternative with local llm
- autocomplete code on airplane with no network
- use open source models for ide code suggestions

## When to choose
- you have a fast Apple Silicon Mac and slow or unreliable internet
- you need code completions that never leave your machine for privacy
- you want a hackable, self-hosted Copilot replacement

## When to avoid
- you have fast internet and want the best completion quality
- you need fast completions with large 34b-class models
- you want a polished one-click installer or non-Mac platforms

## Facets
- artifact type: application
- maturity: experimental
- function: llm-inference, developer-tools, plugin-system
- domain: developer-tools, large-language-models, artificial-intelligence
- platform: python, editor-plugin
- tags: code-completion, github-copilot-alternative, local-llm, vscode, llama-cpp, on-device-ai, macos

## Member repositories
- danielgross/localpilot (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:57.697113+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 2026-08-29T18:40:59.626450+00:00, confidence not recorded.
  - readme: https://github.com/danielgross/localpilot (fetched 2026-08-28T04:07:57.697113+00:00, sha ec8a9d3b2583)
- Data as of 2026-08-30T08:39:29.467469+00:00.