# Lian Agent

> Use this tool when you need to build AI agents with persistent memory and structured task execution tracking, or require a modular system for file operations, mathematical calculations, and web scraping. It solves problems related to task management, data storage, and expert scheduling, providing a comprehensive framework for AI agent development. The Lian Agent takes in task definitions and configuration files, and outputs executable task plans and stored execution history through its PostgreSQL database and OpenAI API integration.

Canonical page: https://skillsregistry.net/skills/yueosa-lian-agent  
JSON: https://api.skillsregistry.net/v1/skills/yueosa-lian-agent

## Description

Lian Agent is a FastAPI-based MCP server implementation that provides file operations, mathematical calculations, and web scraping capabilities through a modular tool architecture. The system features PostgreSQL integration with a custom LianORM for persistent storage of tasks, task steps, tool calls, and memory logs. Built with OpenAI API integration and configurable through TOML files, it supports multi-expert agent scheduling where an administrator LLM automatically generates specialized experts based on tasks, complete with role labels and managed lifecycles. The server includes comprehensive database models and repositories for tracking agent interactions and execution history, making it useful for building AI agents that need persistent memory and structured task execution tracking.

## Trust

- **Trust score (0–1):** 0.59
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/yueosa-lian-agent)
- **Repository:** <https://github.com/yueosa/lian-mcp-llm-agent>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "yueosa-lian-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yueosa-lian-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yueosa-lian-agent/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt