# ggml-org/llama.vim

Vim plugin for LLM-assisted code/text completion

Repository: https://github.com/ggml-org/llama.vim
Canonical: https://ross.abutalabs.com/products/llamavim
Language: Vim Script
License: MIT
License Family: permissive
Topics: llama, llm, vim, vim-plugin, copilot, developer-tool
Last push: 2026-08-25T11:02:19+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 67, longevity 48
- inputs: {"age_days": 674, "days_push": 8, "days_rel": 9, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2149, forks 118 (observed 2026-08-28T04:06:19.253207+00:00)

## What it is
A Vim/Neovim plugin that provides LLM-assisted code and text completion via a local llama.cpp server. It offers fill-in-the-middle (FIM) auto-suggestions and instruction-based editing with configurable keymaps and context handling.

## Use cases
- get AI code completions in vim
- local copilot alternative for neovim
- fill-in-the-middle code completion with llama.cpp
- LLM-assisted text editing in vim
- run code suggestions on local hardware without cloud
- instruction-based code editing from the editor

## When to choose
- you use Vim or Neovim and want privacy-preserving, locally hosted LLM completions
- you already run a llama.cpp server and want editor integration
- you need configurable FIM suggestions and instruction-based edits with large-context support on modest hardware

## When to avoid
- you want a cloud-hosted, zero-setup assistant like GitHub Copilot
- you don't use Vim/Neovim or aren't willing to run a local LLM server
- you need full chat-style IDE assistants rather than inline completion

## Facets
- artifact type: plugin
- maturity: active
- function: llm-inference, developer-tools, editor
- domain: developer-tools, text-editors, large-language-models
- platform: editor-plugin, cli, cross-platform
- tags: vim-plugin, neovim, code-completion, fim, local-llm, llama-cpp, copilot-alternative, ai-assisted-coding

## Member repositories
- ggml-org/llama.vim (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:19.253207+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 2026-08-30T02:50:59.388535+00:00, confidence not recorded.
  - readme: https://github.com/ggml-org/llama.vim (fetched 2026-08-28T04:06:19.253207+00:00, sha 28e1cc3228b1)
- Data as of 2026-08-30T08:39:29.467469+00:00.