CSGHub Lite 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
轻量级本地LLM运行器,支持CSGHub平台
CSGHub Lite 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
轻量级本地LLM运行器,支持CSGHub平台
CSGHub Lite 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:go install(推荐) go install github.com/OpenCSGs/csghub-lite@latest # 方式二:从源码编译 git clone https://github.com/OpenCSGs/csghub-lite cd csghub-lite go build -o csghub-lite . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/OpenCSGs/csghub-lite/releases
# 查看帮助 csghub-lite --help # 基本运行 csghub-lite [options] <input> # 详细使用说明请查阅文档 # https://github.com/OpenCSGs/csghub-lite
# csghub-lite 配置说明 # 查看配置选项 csghub-lite --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export CSGHUB_LITE_CONFIG="/path/to/config.yml"
<p align="center"> <img src="docs/images/apps.png" alt="AI Apps" width="80%"> </p>
A lightweight tool for running large language models locally, powered by models from the CSGHub platform.
Inspired by Ollama, csghub-lite provides model download, local inference, interactive chat, and an OpenAI-compatible REST API — all from a single binary.
csghub-lite can run several model families locally today, with more runtime types planned. The model detail page shows whether a downloaded model is currently supported for local inference.
| Capability | Status | Runtime | Typical models |
|---|---|---|---|
| Text generation / chat | Supported | llama.cpp | Qwen/Qwen3, GLM, Llama, Mistral, DeepSeek distilled GGUF models |
| Embeddings | Supported | llama.cpp | BGE, GTE, E5, Sentence Transformers-compatible embedding models |
| Vision-language chat | Supported | llama.cpp multimodal | Qwen2.5-VL, Gemma 3 / 4 vision, Idefics-style multimodal models |
| Text-to-image | Supported | Diffusers runtime | Qwen-Image, FLUX, Stable Diffusion, PixArt, Sana, CogView, Z-Image |
| Automatic speech recognition | Supported | Python ASR runtime | FunASR, Whisper, Wav2Vec2-family ASR models |
| Image-to-video | Coming soon | - | Stable Video Diffusion, SV3D |
| Text-to-video | Coming soon | - | Video generation Diffusers models |
| Text-to-speech | Coming soon | - | Speech synthesis models |
| Image-to-image | Coming soon | - | Inpaint, img2img, editing pipelines |
curl -fsSL https://hub.opencsg.com/csghub-lite/install.sh | sh
Pin a release version:
curl -fsSL https://hub.opencsg.com/csghub-lite/install.sh | CSGHUB_LITE_VERSION=v0.8.55 sh
irm https://hub.opencsg.com/csghub-lite/install.ps1 | iex
csghub-lite publishes two container images:
opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/csghub-lite:latestopencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/csghub-lite-rocm:latestThe images are lightweight bootstrap runtimes. On container start they download csghub-lite and the matching llama-server; by default this happens only when the persisted install is missing. Persist /root/.csghub-lite so downloaded models, engines, settings, API keys, and usage data survive container restarts. Inside the container, llama-server is installed to /root/.csghub-lite/bin/llama-server, so mounting /root/.csghub-lite also keeps the inference engine across recreates.
```bash
make build-all
```bash
mkdir -p ~/.csghub-lite-docker docker run -d --name csghub-lite \ -p 11435:11435 \ -v ~/.csghub-lite-docker:/root/.csghub-lite \ opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/csghub-lite:latest
Pin the runtime application and llama.cpp engine versions:
bash docker run -d --name csghub-lite \ -p 11435:11435 \ -e CSGHUB_LITE_VERSION=v0.5.10 \ -e CSGHUB_LITE_LLAMA_CPP_TAG=b9158 \ -e CSGHUB_LITE_INSTALL_POLICY=if-version-mismatch \ -v csghub-lite-data:/root/.csghub-lite \ opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/csghub-lite:latest
Force an upgrade on startup:
bash docker run -d --name csghub-lite \ -p 11435:11435 \ -e CSGHUB_LITE_INSTALL_ALWAYS=1 \ -v csghub-lite-data:/root/.csghub-lite \ opencsg-registry.cn-beijing.cr.aliyuncs.com/opencsghq/csghub-lite:latest
For AMD GPU hosts with ROCm support:
bash
csghub-lite login ```
Note: The install script automatically installs llama-server (required for inference). If you installed from source, install it separately: brew install llama.cpp (macOS) or download from llama.cpp releases.
csghub-lite launch claude-code --model "glm-4-flash"
csghub-lite launch codex --model "Qwen/Qwen2.5-Coder-7B"
csghub-lite launch pi --model "moonshot-v1-8k" ```
Configuration is stored at ~/.csghub-lite/config.json.
The CLI and Web UI expose a convenience storage_dir setting. When you set it, csghub-lite expands it into the persisted model_dir and dataset_dir.
| Key | Default | Description |
|---|---|---|
storage_dir | ~/.csghub-lite | Shared local storage root for models and datasets |
server_url | https://hub.opencsg.com | CSGHub platform URL |
ai_gateway_url | https://ai.space.opencsg.com | AI Gateway URL for cloud inference models |
model_dir | ~/.csghub-lite/models | Effective local model storage directory |
dataset_dir | ~/.csghub-lite/datasets | Effective local dataset storage directory |
listen_addr | :11435 | API server listen address |
token | (none) | CSGHub access token |
Switch to a private CSGHub deployment:
csghub-lite config set server_url https://my-private-csghub.example.com
| Command | Description |
|---|---|
csghub-lite run <model> | Pull, start server, and chat (all automatic) |
csghub-lite chat <model> | Chat with a locally downloaded model |
csghub-lite ps | List currently running models and their keep-alive |
csghub-lite stop <model> | Stop/unload a running model |
csghub-lite serve | Start the API server (auto-started by run) |
csghub-lite restart | Restart the background API server |
csghub-lite pull <model> | Download a model from CSGHub |
csghub-lite list / ls | List locally downloaded models |
csghub-lite show <model> | Show model details (format, size, files) |
csghub-lite rm <model> | Remove a locally downloaded model |
csghub-lite login | Set CSGHub access token |
csghub-lite search <query> | Search models on CSGHub |
csghub-lite config set <key> <value> | Set configuration |
csghub-lite config get <key> | Get a configuration value |
csghub-lite config show | Show current configuration |
csghub-lite uninstall | Remove csghub-lite and llama-server, preserving local data unless --all is set |
csghub-lite --version | Show version information |
Model names use the format namespace/name, e.g. Qwen/Qwen3-0.6B-GGUF.
The server listens on localhost:11435 by default.
For full endpoint details and examples, see the REST API Reference.
If the local server is running, you can also open the interactive API docs in your browser: http://localhost:11435/api-docs.html
run — Downloads the model if not present, auto-starts the background server, and opens a chat session. After you exit, the model stays loaded for 5 minutes by default so the next run is instant. Use --keep-alive -1 to keep it loaded until you stop it manually.chat — Starts a chat session with a model that is already downloaded. Supports --system flag for custom system prompts.```bash
csghub-lite 是一个轻量级工具,用于在本地运行大型语言模型,依赖于 CSGHub 平台的模型。它受到 Ollama 的启发,提供模型下载、本地推理、交互式聊天和 OpenAI 兼容的 REST API —— 从单个二进制文件中获得所有功能。
csghub-lite 支持本地推理,目前支持多种模型家族,包括文本生成/聊天、嵌入等。模型详细页面显示下载的模型是否支持本地推理。
环境依赖与系统要求
快速安装(Linux/macOS) ```bash curl -fsSL https://hub.opencsg.com/csghub-lite/install.sh | sh ``` 快速安装(Windows PowerShell) ```powershell irm https://hub.opencsg.com/csghub-lite/install.ps1 | iex ```
快速启动 ```bash csghub-lite run <model> ```
配置说明 MCP、环境变量、关键参数等
CLI 命令 | Command | Description | | --- | --- | | `csghub-lite run <model>` | Pull, start server, and chat (all automatic) | | `csghub-lite chat <model>` | Chat with a locally downloaded model | | `csghub-lite ps` | List currently running models and their keep-alive | | `csghub-lite stop <model>` | Stop/unload ... REST API The server listens on `localhost:11435` by default.
工作流 / 模块说明 - 第三方提供商 —— 整合 OpenAI、DeepSeek、MiMo、Kimi、BigModel、Qianfan、MiniMax、OpenRouter 等 OpenAI 兼容 API - 编码代理 —— 一键配置 Claude Code、Codex、Pi、OpenCode - AI 应用 —— 一键设置 OpenClaw、CSGClaw、Dify、AnythingLLM
轻量级LLM运行器,支持CSGHub平台,值得关注
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,CSGHub Lite 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | csghub-lite |
| 原始描述 | 开源AI工作流:csghub-lite is a lightweight local LLM runner for the CSGHub platform. One comma。⭐27 · Go |
| Topics | AILLMCSGHubGo |
| GitHub | https://github.com/OpenCSGs/csghub-lite |
| License | Apache-2.0 |
| 语言 | Go |
收录时间:2026-06-06 · 更新时间:2026-06-06 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端