# huggingface/llm-vscode

LLM powered development for VSCode

Repository: https://github.com/huggingface/llm-vscode
Canonical: https://ross.abutalabs.com/products/llm-vscode
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-05-26T10:32:20+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 8, longevity 92
- inputs: {"age_days": 1294, "days_push": 99, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1313, forks 142 (observed 2026-08-28T04:04:20.306797+00:00)

## What it is
A VSCode extension providing LLM-powered features like Copilot-style ghost-text code completion, with configurable backends including the Hugging Face Inference API, Ollama, and OpenAI-compatible endpoints. It uses llm-ls as its backend and includes code attribution checking against The Stack dataset.

## Use cases
- get copilot-style code completion in vscode
- use local llm models for code completion via ollama
- connect vscode to hugging face inference api for code generation
- check if generated code comes from the stack dataset
- use starcoder or custom models as coding assistant in editor

## When to choose
- you want LLM code completion in VSCode with a choice of models and backends
- you prefer self-hosted or OpenAI-compatible endpoints instead of a proprietary assistant
- you need provenance/attribution checks on generated code

## When to avoid
- you want a full chat-based coding agent rather than completion-focused features
- you use an editor other than VSCode (see llm.nvim or llm-intellij instead)
- you are unwilling to manage API tokens or rate limits on the free Inference API tier

## Facets
- artifact type: plugin
- maturity: active
- function: llm-inference, editor, plugin-system
- domain: developer-tools, large-language-models, text-editors
- platform: editor-plugin, cross-platform
- tags: vscode-extension, code-completion, ghost-text, huggingface, code-attribution, llm-ls

## Member repositories
- huggingface/llm-vscode (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.306797+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 2026-08-30T04:48:52.107173+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/llm-vscode (fetched 2026-08-28T04:04:20.306797+00:00, sha 59b0ef347bca)
- Data as of 2026-08-30T08:39:29.467469+00:00.