workflowstacks
mcp-server

LiveAgent: AI Agent Client

Get a customizable AI agent desktop client with Webui access.
1,916 stars219 forksTypeScriptGuide quality 8/10Updated 9/2/2026100% free · open source
What it does

LiveAgent provides a customizable AI agent desktop client with Webui access, allowing founders to creatively customize and expand their AI tools

When to use it
  • •You need a desktop client for your AI agent with web UI access
  • •Your startup requires a highly customizable AI tool
  • •You want to leverage a popular open-source AI project with 1.2k+ GitHub stars
Ready-to-paste prompt
Modify the `config.json` file to add a custom skill by adding a new object to the `skills` array, then restart the agent with `npm run start`
Heads up: Ensure you have Node.js and npm installed on your system, as LiveAgent is built with TypeScript and requires these to run
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/liveagent && curl -fsSL https://workflowstacks.com/api/skills/liveagent/claude-skill -o ~/.claude/skills/liveagent/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 LiveAgent: AI Agent Client works
Codeflow
Free to inspect

LiveAgent: AI Agent Client is a very large TypeScript project (~408k lines across 1311 code files, plus 451 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, MIT license, has a test suite.

Size
Very large codebase
~408k lines · 1311 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
Node.js · Rust · Docker
No API keys detected
TypeScript 50%Rust 22%JavaScript 21%Go 5%CSS 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    Cargo.toml
    Dependencies and the commands it exposes
What's in each folder
docs/Documentation81 files
crates/agent-gui/Folder967 files
crates/agent-ui/Folder499 files
crates/agent-gateway/Folder389 files
scripts/Helper scripts24 files
crates/virtual-core/Folder14 files
.github/CI / automation (GitHub Actions)23 files
.codegraph/Tool / agent settings1 files
READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month
Quick Actions
Details
Creator
Stack-Cairn
Language
TypeScript
Category
mcp-server
Published
5/24/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 242,984
ECC: Optimize Performance
Get optimized performance with ECC, a research-first agent harness system for founders working with AI agents and developer tools like Claude Code and Codex
mcp-server★ 154,417
Dify: Streamline Workflow
Get a production-ready platform with Dify. For founders needing agentic workflow development.
mcp-server★ 150,115
open-webui: Easy AI Interface
Get a user-friendly AI interface with open-webui, supporting Ollama and OpenAI API, for founders, with 145k+ GitHub stars
mcp-server★ 113,199
Graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
mcp-server★ 106,674
gemini-cli: AI in your terminal
Get AI power with gemini-cli, for founders, 105k+ GitHub stars
mcp-server★ 82,036
LobeHub: 24/7 AI Team Management
Founders get organized AI operations with LobeHub. For startup founders managing AI teams.