https://github.com/emrahcom/llama-native
A lightweight Deno client for llama.cpp with zero dependencies. Supports OpenAI-compatible chat and native GBNF grammar completions.
https://github.com/emrahcom/llama-native
deno jsr llama llama-cpp llamacpp
Last synced: 5 days ago
JSON representation
A lightweight Deno client for llama.cpp with zero dependencies. Supports OpenAI-compatible chat and native GBNF grammar completions.
- Host: GitHub
- URL: https://github.com/emrahcom/llama-native
- Owner: emrahcom
- License: mit
- Created: 2026-04-19T14:35:27.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2026-05-26T16:23:53.000Z (8 days ago)
- Last Synced: 2026-05-26T16:27:30.809Z (8 days ago)
- Topics: deno, jsr, llama, llama-cpp, llamacpp
- Language: TypeScript
- Homepage: https://jsr.io/@emrahcom/llama-native
- Size: 87.9 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# llama-native
**Still in alpha**
A lightweight Deno client for llama.cpp with zero dependencies. Supports
OpenAI-compatible chat and native GBNF grammar completions.
## Usage
Assuming that `llama-server` is running in your local environment...
```Typescript
import { Llama } from "jsr:@emrahcom/llama-native";
const llama = new Llama();
const res = await llama.v1.chat.create({
messages: [
{ role: "user", content: "Hello!" },
],
});
console.log(res.choices[0].message.content);
```
See also [examples](examples).
## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file
for details.