# huggingface/llm.nvim

LLM powered development for Neovim

Repository: https://github.com/huggingface/llm.nvim
Canonical: https://ross.abutalabs.com/products/llmnvim
Language: Lua
License: Apache-2.0
License Family: permissive
Topics: neovim, neovim-plugin, lua
Last push: 2026-05-26T10:32:29+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 35, longevity 86
- inputs: {"age_days": 1214, "days_push": 99, "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 1186, forks 59 (observed 2026-08-28T04:03:55.143590+00:00)

## What it is
llm.nvim is a Neovim plugin that brings LLM-powered features like ghost-text code completion to the editor, using llm-ls as its backend. It supports the Hugging Face Inference API or custom HTTP endpoints, letting users pick any model and automatically fitting prompts to the model's context window.

## Use cases
- get copilot-style code completion in neovim
- use hugging face models for code completion in vim
- connect neovim to a local LLM endpoint
- choose my own model for AI code suggestions
- AI ghost text completion in neovim
- avoid rate limits with a self-hosted LLM backend for editing

## When to choose
- you use Neovim and want LLM code completion with model choice
- you want to plug in your own HTTP backend or the Hugging Face Inference API
- you prefer an open-source Copilot alternative in the terminal

## When to avoid
- you use VS Code or another editor rather than Neovim
- you need full chat/agent IDE features beyond completion
- you cannot access any LLM inference endpoint

## Facets
- artifact type: plugin
- maturity: active
- function: llm-inference, editor, plugin-system, http-client
- domain: large-language-models, developer-tools, text-editors, artificial-intelligence
- platform: editor-plugin, cli
- tags: neovim, code-completion, ghost-text, huggingface, lua, llm-ls, copilot-alternative

## Member repositories
- huggingface/llm.nvim (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.143590+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 2026-08-30T06:23:53.781572+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/llm.nvim (fetched 2026-08-28T04:03:55.143590+00:00, sha 75f05e1d77cb)
- Data as of 2026-08-30T08:39:29.467469+00:00.