Content
<p align="center">
<a href="https://www.managelm.com">
<img src="https://www.managelm.com/assets/ManageLM.png" alt="ManageLM" height="50">
</a>
</p>
<h3 align="center">ManageLM Server</h3>
<p align="center">
Manage your servers with natural language — the self-hosted control plane for <a href="https://github.com/managelm/managelm-agent">ManageLM agents</a>.
</p>
<p align="center">
<a href="LICENSE"><img src="https://img.shields.io/badge/license-source--available-blue" alt="License"></a>
<a href="https://www.managelm.com"><img src="https://img.shields.io/badge/website-managelm.com-cyan" alt="Website"></a>
<a href="https://app.managelm.com/doc/"><img src="https://img.shields.io/badge/docs-documentation-green" alt="Docs"></a>
<a href="https://hub.docker.com/r/managelm/portal"><img src="https://img.shields.io/badge/docker-managelm%2Fportal-blue?logo=docker" alt="Docker"></a>
<img src="https://img.shields.io/badge/platform-linux-lightgrey" alt="Platform">
</p>
<p align="center">
<img src="https://raw.githubusercontent.com/managelm/managelm-agent/main/assets/portal.png" alt="ManageLM Portal — dashboard with agent monitoring, task history, and natural language interface" width="700">
</p>
---
No more rigid dashboards and scripts. Tell Claude what you need — ManageLM agents execute it on your Linux and Windows servers, scoped to only the commands you allow.
```
You: "Install nginx, enable it, open port 443, and run a security audit"
Portal: Execution Plan
┌──────────────────────────────────────────────────────┐
│ 1) packages → Install nginx │
│ 2) services → Enable and start nginx │
│ 3) firewall → Open port 443/tcp │
│ 4) security → Run full security audit │
└──────────────────────────────────────────────────────┘
✓ All steps completed. Security audit: 47 checks passed, 3 warnings.
```
## Why ManageLM Server?
- **Natural language to server execution in seconds** — describe what you need, the agent picks the right skill and runs the right commands.
- **32+ built-in skills** — packages, services, firewall, web servers, databases, containers, certificates, users, storage, compliance, and more.
- **Security is the architecture** — 4-layer protection: injection blocking, binary allowlist, destructive argument guard, and kernel sandbox (Landlock + seccomp-bpf). Read-only by default.
- **Zero inbound ports** — agents connect outward via WebSocket. No SSH, no VPN, no attack surface.
- **Local or cloud AI** — agents use Ollama, LocalAI, or any OpenAI-compatible LLM. Your data stays on your servers.
- **100% free for up to 10 agents** — no catches, no time limits.
## Quick Start
### Option 1: Self-extracting installer
Download the [latest release](https://github.com/managelm/managelm-server/releases/latest), extract, and run:
```bash
gunzip managelm-1.3.2-linux-x64.sh.gz
sudo bash managelm-1.3.2-linux-x64.sh
```
The installer bundles its own Node.js runtime — **no prerequisites** on the target server. It prompts for a service user and port, installs to `/opt/managelm-server/`, and registers a systemd service.
After installation:
```bash
# Configure database and Redis
sudo vi /opt/managelm-server/portal/.env
# Start the portal
systemctl start managelm-portal
# Install your first agent
curl -fsSL https://your-server/install | bash
```
### Option 2: Docker
```bash
curl -fSL https://app.managelm.com/doc/docker-compose.yml -o docker-compose.yml
curl -fSL https://app.managelm.com/doc/.env.example -o .env
# Edit .env with your settings, then:
docker compose up -d
```
### Option 3: SaaS (zero setup)
Just go to [app.managelm.com](https://app.managelm.com) and create an account. Free for up to 10 agents.
## Prerequisites
| Component | Required for |
|-----------|-------------|
| **PostgreSQL 15+** | Application database |
| **Redis 7+** (or Valkey) | Sessions, pub/sub, rate limiting |
Node.js is bundled in the installer. Docker images include everything.
## Fleet Management
<p align="center">
<img src="https://raw.githubusercontent.com/managelm/managelm-agent/main/assets/infrastructure.png" alt="ManageLM Infrastructure — monitoring dashboard with server health, CPU, memory, disk, and network metrics" width="700">
</p>
Monitor your entire fleet from a single pane — health status, CPU, memory, disk, network. Run tasks across groups, trigger security audits, generate compliance reports, manage certificates, and track every change.
## Features
| Category | Capabilities |
|----------|-------------|
| **Task execution** | Natural language tasks, multi-step planning, file transfers, interactive Q&A |
| **Security** | Automated audits (SSH, firewall, TLS, users, packages), PDF reports, compliance frameworks |
| **Monitoring** | CPU, memory, disk, services, custom checks, email/webhook alerts |
| **PKI** | Internal CA, Let's Encrypt ACME (HTTP-01, DNS-01), wildcard certs, auto-renewal |
| **Backups** | Scheduled backups to S3-compatible storage, retention policies |
| **Inventory** | Hardware, packages, services, containers, network — auto-discovered |
| **Cloud connectors** | AWS EC2 fleet discovery and import |
| **Multi-tenant** | Accounts, roles, per-user permissions, team management |
## Architecture
```
┌─────────────┐ MCP (HTTPS) ┌──────────────────┐ WebSocket/HTTPS ┌─────────────┐
│ Claude │ ◄─────────────────────► │ ManageLM Server │ ◄───────────────────► │ Agent │
│ (MCP Client)│ │ (this project) │ │ (on host) │
└─────────────┘ └──────────────────┘ └─────────────┘
│
┌──────┴──────┐
│ PostgreSQL │
│ Redis/Valkey│
└─────────────┘
```
## Integrations
Works with your favorite AI tools:
- [Claude Code Extension](https://github.com/managelm/claude-extension) — MCP integration for Claude Desktop and Claude Code
- [VS Code Extension](https://github.com/managelm/vscode-extension) — `@managelm` in Copilot Chat
- [ChatGPT Plugin](https://github.com/managelm/openai-gpt) — manage servers from ChatGPT
- [n8n Plugin](https://github.com/managelm/n8n-plugin) — infrastructure automation workflows
- [Slack Plugin](https://github.com/managelm/slack-plugin) — notifications and commands in Slack
- [OpenClaw Plugin](https://github.com/managelm/openclaw-plugin) — OpenClaw integration
## Upgrading
Download the new release and run it on the same server. The installer detects the existing installation, preserves your `.env`, and upgrades in place:
```bash
gunzip managelm-1.3.3-linux-x64.sh.gz
sudo bash managelm-1.3.3-linux-x64.sh
```
## Links
- [Website](https://www.managelm.com)
- [Documentation](https://app.managelm.com/doc/)
- [Docker Hub](https://hub.docker.com/r/managelm/portal)
- [ManageLM Agent](https://github.com/managelm/managelm-agent)
## License
- ManageLM is Free for non-commercial use with up to 10 registered agents.
- Commercial use requires a license from [RCDevs S.A.](https://www.managelm.com)
- [Terms and Conditions](https://www.managelm.com/terms.html)
- [Privacy](https://www.managelm.com/terms.html#privacy)
