Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
LLM powered development for VSCode
| Date | Stars |
|---|---|
| 2026-07-31 | 1313 |
| 2026-08-02 | 1313 |
| 2026-08-03 | 1313 |
| 2026-08-06 | 1313 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# LLM powered development for VSCode
**llm-vscode** is an extension for all things LLM. It uses [**llm-ls**](https://github.com/huggingface/llm-ls) as its backend.
We also have extensions for:
* [neovim](https://github.com/huggingface/llm.nvim)
* [jupyter](https://github.com/bigcode-project/jupytercoder)
* [intellij](https://github.com/huggingface/llm-intellij)
Previously **huggingface-vscode**.
> [!NOTE]
> When using the Inference API, you will probably encounter some limitations. Subscribe to the *PRO* plan to avoid getting rate limited in the free tier.
>
> https://huggingface.co/pricing#pro
## Features
### Code completion
This plugin supports "ghost-text" code completion, à la Copilot.
### Choose your model
Requests for code generation are made via an HTTP request.
You can use the Hugging Face [Inference API](https://huggingface.co/inference-api) or your own HTTP endpoint, provided it adheres to the APIs listed in [backend](#backend).
The list of officially supported models is located in the config template section.
### Always fit within the context window
The prompt sent to the model will always be sized to fit within the context window, with the number of tokens determined using [tokenizers](https://github.com/huggingface/tokenizers).
### Code attribution
Hit `Cmd+shift+a` to check if the generated code is in [The Stack](https://huggingface.co/datasets/bigcode/the-stack).
This is a rapid first-pass attribution check using [stack.dataportraits.org](https://stack.dataportraits.org).
We check for sequences of at least 50 characters that match a Bloom filter.
This means false positives are possible and long enough surrounding context is necesssary (see the [paper](https://dataportraits.org/) for details on n-gram striding and sequence length).
[The dedicated Stack search tool](https://hf.co/spaces/bigcode/search) is a full dataset index and can be used for a complete second pass.
## Installation
Install like any other [vscode extension](https://marketplace.visualstudio.com/items?itemName=HuggingFace.huggingface-vscode).
By default, this extension uses [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) & [Hugging Face Inference API](https://huggingface.co/inference-api) for the inference.
#### HF API token
You can supply your HF API token ([hf.co/settings/token](https://hf.co/settings/token)) with this command:
1. `Cmd/Ctrl+Shift+P` to open VSCode command palette
2. Type: `Llm: Login`
If you previously logged in with `huggingface-cli login` on your system the extension will read the token from disk.
## Configuration
You can check the full list of configuration settings by opening your settings page (`cmd+,`) and typing `Llm`.
### Backend
You can configure the backend to which requests will be sent. **llm-vscode** supports the following backends:
- `huggingface`: The Hugging Face Inference API (default)
- `ollama`: [Ollama](https://ollama.com)
- `openai`: any OpenAI compatible API (e.g. [llama-cpp-python](https://github.com/abetlen/llama-cpp-python))
- `tgi`: [Text Generation Inference](https://github.com/huggingface/text-generation-inference)
Let's say your current code is this:
```py
import numpy as np
import scipy as sp
{YOUR_CURSOR_POSITION}
def hello_world():
print("Hello world")
```
The request body will then look like:
```js
const inputs = `{start token}import numpy as np\nimport scipy as sp\n{end token}def hello_world():\n print("Hello world"){middle token}`
const data = { inputs, ...configuration.requestBody };
const model = configuration.modelId;
let endpoint;
switch(configuration.backend) {
// cf URL construction
let endpoint = build_url(configuration);
}
const res = await fetch(endpoint, {
body: JSON.stringify(data),
headers,
method: "POST"
});
const json = await res.json() as { generated_text: string };
```
Note that the example above is a simplified version to explain what is happening under the hood.
#### URL construction
The endpoint URL thExcerpt of 9,096 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c0b137e0cbb3e03b, llm:Repository description: 'LLM powered development for VSCode' (huggingface/llm-vscode). TypeScript extension for VSCode integrating LLMs into development workflows.
matched fp:c0b137e0cbb3e03b, llm:Repository description: 'LLM powered development for VSCode' (huggingface/llm-vscode). TypeScript extension for VSCode integrating LLMs into development workflows.
matched fp:c0b137e0cbb3e03b, llm:Repository description: 'LLM powered development for VSCode' (huggingface/llm-vscode). TypeScript extension for VSCode integrating LLMs into development workflows.
