ai-agent

csghub-server: Manage AI

Name: csghub-server: Manage AI
Author: OpenCSGs

Get a backend server to manage datasets and models with csghub-server, for founders leveraging AI

1,046 stars230 forksGoGuide quality 8/10Updated 8/28/2026100% free · open source

What it does

CSGHub-server is a backend server for managing datasets, models, and running model inference, finetuning, and application spaces for AI-related tasks

When to use it

•You need a centralized platform to organize and manage your AI datasets and models
•You want to run model inference, finetuning, or application spaces in a controlled environment
•You are building an AI-powered application and need a backend server to support your AI workflows

Ready-to-paste prompt

Use the `curl -X POST -H 'Content-Type: application/json' -d '{"name": "my-model", "type": "classification"}' http://localhost:8080/models` command to create a new model

Heads up: Ensure you have Go installed on your system and the `GOPATH` environment variable is set, as the server is built using Go and relies on the Go ecosystem

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/csghub-server && curl -fsSL https://workflowstacks.com/api/skills/csghub-server/claude-skill -o ~/.claude/skills/csghub-server/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How csghub-server: Manage AI works

Codeflow

Free to inspect

Csghub-server: Manage AI is a very large Go project (~473k lines across 2670 code files, plus 2 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~473k lines · 2670 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Go · Docker

No API keys detected

Go 97%Python 2%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
cmd/csghub-server/main.go
Where the program starts running
4
go.mod
Dependencies and the commands it exposes

What's in each folder

component/Frontend / UI217 files

api/Backend / API202 files

cmd/Command-line entry points62 files

docs/Documentation14 files

builder/Folder1119 files

_mocks/Folder322 files

common/Folder299 files

aigateway/Folder224 files

READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/csghub-server && curl -fsSL https://workflowstacks.com/api/skills/csghub-server/claude-skill -o ~/.claude/skills/csghub-server/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

OpenCSGs

Language