推論、デプロイ、ランタイム

jan

janhq/jan

A local AI chat application for running models on a personal computer.

★ 44.3Kスター
⑂ 3Kフォーク数
508未解決の問題
TypeScript言語
ライセンス
Q80編集部スコア

概要

A local AI chat application for running models on a personal computer. The repository is maintained under janhq on GitHub. Its primary language is TypeScript. See the [project README](https://github.com/janhq/jan#readme) for the supported workflows.

主な機能

  • A local AI chat application for running models on a personal computer.

要件、インストール、クイックスタート

Use the upstream download or installation instructions for your operating system. Check the model, memory and accelerator requirements for the workload you intend to run.

[Read the upstream installation and quickstart instructions](https://github.com/janhq/jan#readme).

使用方法

Start with the documented local example, confirm it runs with your resources, then connect it to your application using the supported interface.

[Usage examples and configuration reference](https://github.com/janhq/jan#readme).

モデルの互換性とユースケース

リポジトリのメタデータにモデル互換性の記載がありません。

ライセンスとリスクに関する注意事項

The README identifies Apache 2.0. GitHub’s automated license field is not a definitive SPDX match; consult the repository license file.

Source review 2026-09-05: GitHub search metadata and repository README. No runtime benchmark performed. License metadata: NOASSERTION.

リリースとメンテナンス

[View upstream releases](https://github.com/janhq/jan/releases).

vllm

vllm-project/vllm

★ 89.5KPython

sglang

sgl-project/sglang

★ 32.2KPython

OpenVINO

openvinotoolkit/openvino

★ 10.6KC++

GPUStack

gpustack/gpustack

★ 5.4KPython