# ManageLM — Full Product Information

> AI-powered Linux and Windows server management platform. Secure by design.

## What is ManageLM?

ManageLM is a server management platform that enables teams to manage Linux and Windows servers through natural language. Users talk to Claude (via Anthropic's MCP protocol), and ManageLM agents execute tasks locally on servers using a local LLM — with hard-enforced security at every layer.

## How It Works

1. **Talk to Claude**: Users describe what they need in natural language through the Claude app or any supported plugin (ChatGPT, VS Code Copilot, Slack, n8n). Examples: "Run a security audit on all production servers and fix critical findings", "Check disk usage across all production servers", "Deploy the latest release to staging and run health checks".

2. **Portal Authenticates & Routes**: The ManageLM cloud portal verifies identity via OAuth 2.0, checks permissions (RBAC), validates the request against assigned skills, and dispatches the task over a secure WebSocket channel to the target agent.

3. **Agent Executes Locally**: A lightweight agent on the server uses Ollama (or any compatible LLM) to interpret the task, generate commands, validate each command against the skill's allowlist, and execute. Sensitive data never leaves the machine.

## Security Architecture

ManageLM uses a three-layer security enforcement model:

### Layer 1: Skill Scope
Skills define what categories of operations an agent can perform. Each agent is assigned specific skills with explicit boundaries.

### Layer 2: Command Allowlisting
Every AI-generated command is validated against an explicit allowlist defined in code — not prompts. Any command outside the allowlist is blocked. This is hard-enforced, not advisory.

### Layer 3: Execution Sandbox
Each task execution is constrained: max 10 turns, 120-second timeout, 8KB output cap. File operations use structured `<edit>` and `<write>` tags handled in Python (no shell escaping). Kernel-level Landlock and seccomp sandboxing. Every operation is logged in a full audit trail.

### Additional Security Features
- **Local LLM**: Task interpretation runs locally via Ollama or any supported provider. Passwords, configs, logs — nothing leaves the machine.
- **Read-Only by Default**: Agents with no allowed_commands can only run read-only operations.
- **Zero Inbound Ports**: Agents connect outward via WebSocket. Servers never expose a port. No SSH, no VPN, no attack surface.
- **Secrets Hidden from AI**: Secrets are environment variables. The LLM only sees $VAR_NAME — actual values are injected at execution time.
- **LLM is Untrusted by Design**: The AI generates commands, but every command is validated in code before execution. Prompt injection or hallucinations are blocked.

## Built-in Skills (33 skills, 396 operations across Linux & Windows)

Each skill defines exact allowed commands — nothing more, nothing less. Skills are shipped as 55 platform-specific bundles (30 Linux + 25 Windows) covering 219 Linux operations and 177 Windows operations.

- **Containers & Kubernetes**: Docker, Podman, kubectl, Helm, Compose
- **Developer Tools & Scripting** (Linux): Scripts, compiling, builds, tests, linters, Git
- **Email Server Management**: Postfix/Dovecot (Linux), Exchange Server (Windows)
- **File & Directory Management**: File operations, permissions, compression
- **File Sharing & FTP**: NFS/Samba (Linux), SMB/DFS/FTP (Windows)
- **SQL Database Management**: PostgreSQL, MySQL, SQL Server
- **NoSQL Database Management** (Linux): MongoDB, Redis
- **Web Server Management**: nginx/Apache (Linux), IIS (Windows)
- **Web Application Management** (Linux): Node.js, Python, PHP apps
- **Services & Process Management**: systemd (Linux), Windows Services
- **Packages & Updates**: apt/dnf/yum (Linux), winget/choco/Windows Update (Windows)
- **Users & Access Management**: Local users, groups, ACLs
- **Security & Hardening**: fail2ban/SELinux (Linux), Defender/BitLocker (Windows)
- **Firewall Management**: UFW/iptables/nftables (Linux), Windows Firewall
- **Network Configuration**: IP, DNS, routing, NIC teaming
- **DNS Server Management**: BIND/dnsmasq (Linux), Windows DNS Server
- **VPN & Tunnel Management**: WireGuard, OpenVPN, IPsec, RRAS (Windows)
- **Certificates & PKI**: OpenSSL/Let's Encrypt (Linux), Certificate Store (Windows)
- **Backup & Restore**: tar/rsync (Linux), Windows Server Backup
- **Storage & Disk Management**: LVM/partitions (Linux), diskpart/volumes (Windows)
- **System Configuration**: hostname, timezone, features, environment
- **Log Analysis**: journalctl (Linux), Event Log (Windows)
- **Virtualization**: KVM/Proxmox (Linux), Hyper-V (Windows)
- **Automation**: Ansible/Terraform (Linux), Task Scheduler (Windows)
- **Active Directory** (Windows): AD users, groups, OUs, GPO
- **Remote Desktop Services** (Windows): RDP sessions, NLA, RDS collections
- **Registry Management** (Windows): Browse, edit, export registry keys
- **Directory Services & LDAP** (Linux): OpenLDAP, FreeIPA
- **Message Queue Management** (Linux): RabbitMQ, Kafka
- **Monitoring & Alerting** (Linux): System monitoring
- **Proxy & Cache** (Linux): Reverse proxy configuration
- **LLM Server Management** (Linux): Ollama, LocalAI
- **Base Utilities**: Core read-only operations available to all agents
- **Custom Skills**: Users can create unlimited custom skills with RAG documentation

## Built-in Agent Capabilities (no skill required)

- **Security Audits**: 19+ deterministic checks with LLM-powered analysis and automated remediation
- **System Inventory**: 15+ checks for services, packages, containers, listening ports, and more
- **SSH & Sudo Access**: Discovers all authorized_keys and sudoers rules across servers, maps SSH key fingerprints to team member profiles for identity resolution. Fleet-wide PDF access reports.
- **Activity Audit**: Collects login activity, failed authentication, sudo/elevated commands, and file changes from standard Linux logs (no auditd required) and the Windows Event Viewer. Search across the fleet without dispatching new commands.
- **Dependency Scanning**: Listening ports and config file parsing for service discovery
- **Compliance & Frameworks**: Automatically evaluate fleet against CIS Level 1, CIS Docker, SOC 2, PCI DSS, ISO 27001, NIS2, NIST CSF, and HIPAA. Drift detection alerts when previously passing rules start failing. Generate per-framework audit evidence PDFs. Custom frameworks via JSON.
- **File Transfers**: Upload/download files up to 25MB with change tracking
- **Change Tracking**: 30-day retention of all file modifications via git-based tracking
- **Structured File Operations**: `<edit>` (find-and-replace) and `<write>` (create/overwrite) tags for deterministic file I/O — no shell escaping issues
- **Service Monitors**: 46 service types (TCP, HTTP, ICMP) with email, webhook and in-app alerts. Response time history and hourly rollups for trend analysis.
- **Certificate Management (PKI)**: Internal CA + Let's Encrypt ACME (http-01 and dns-01). Agent-side keypair generation (CSR flow — private keys never leave the server). Automatic daily renewal, CRL generation, public CA/CRL endpoints for trust chain installation.
- **System Backups**: End-to-end encrypted filesystem backups to your own S3 storage (OVH, AWS, Cloudflare R2, Backblaze B2, Wasabi, Scaleway, MinIO). Per-backup AES-256-CBC + HMAC-SHA256 keys, agent-side encryption so ManageLM never sees backup content. Configurable schedules (hourly, 6h, daily, weekly, monthly), FIFO retention, restore-to-any-agent, optional service quiesce (stop/restart databases for consistent snapshots), streaming decrypt downloads, detach-on-agent-delete with Reassign workflow.
- **Cloud Inventory Connectors**: Read-only inventory sync from AWS, Azure, GCP, OpenStack, Proxmox, and VMware. Search instances, networks, and resources across cloud providers alongside on-prem agents.
- **SIEM Connectors**: Forward audit events, alerts, and task activity to Elastic, Splunk, or any HMAC-signed Webhook endpoint.
- **Pentests** (Pro/Enterprise): Authorized external scans of agents using Nmap (service discovery), Nuclei (vulnerability templates), and testssl.sh (TLS hardening). Findings are tagged with framework references (CIS, PCI DSS, SOC 2, ISO 27001, NIS2, NIST CSF, HIPAA) and rolled into severity-scored reports.

## Portal Meta Tools

These tools are always available to MCP clients regardless of skill assignments:

- search_agents, get_agent_info — Agent discovery and health monitoring
- get_agent_skills, list_available_skills — Skill management
- list_team_members — Team members with roles, permissions, and registered SSH public keys
- get_account_info — Account plan and usage information
- run_security_audit, search_security — Security audit execution and search
- run_inventory_scan, search_inventory — System inventory scanning and search
- run_access_scan, search_ssh_keys, search_sudo_rules — SSH & sudo access scanning, key search with identity mapping, sudo privilege search
- run_activity_scan, search_activity — Activity scan execution and search across logins, failed auth, sudo, and file changes
- list_connectors, search_cloud, get_cloud_info — Cloud connector discovery and search across AWS, Azure, GCP, OpenStack, Proxmox, VMware
- search_monitors — Service monitor discovery and filtering
- search_certificates — Certificate discovery with status, source, agent, and expiry filters
- search_backups — System backup discovery with agent, status, and schedule
- get_task_status, get_task_history, get_task_changes, answer_task, revert_task — Task monitoring, change tracking, and rollback
- send_email — Email reports and notifications

## Plugins & Integrations

- **Claude** (MCP Extension): Native integration via Anthropic's MCP protocol. Natural language tasks, multi-server targeting, file transfers, security audits, task history and revert.
- **ChatGPT** (OpenAI GPT): OAuth per-user authentication. Natural language tasks, security audits, inventory scans. Works with SaaS and self-hosted.
- **VS Code** (Copilot Extension): @managelm participant in Copilot Chat. 13 built-in tools, multi-server targeting, security audits, inventory scans.
- **Slack** (Slack App): Real-time alerts, /managelm commands, agent approval, task execution, channel routing, HMAC verification.
- **n8n** (Community Node): Workflow automation integration for n8n.

## Supported LLM Providers

Agents support 13 LLM providers: Anthropic, OpenAI, Gemini, xAI (Grok), Groq, Mistral, DeepSeek, Together, Fireworks, Perplexity, Cohere, Ollama, LocalAI.

## Platform Features

- **Multi-Tenant Teams**: Owner, admin, member roles with granular permissions. Invite teammates, scope access per server or group.
- **Server Groups**: Organize agents into groups. Run operations across entire groups with a single request.
- **Scheduled Tasks**: Cron-based schedules for backups, log rotation, health checks — all automated.
- **Webhooks & API Keys**: Real-time notifications on events. Full REST API for integration into existing workflows.
- **Full Audit Trail**: Every action logged with timestamps, IPs, and full context.
- **Passkeys & MFA**: WebAuthn/FIDO2 passwordless login. Multi-factor auth and IP whitelisting for MCP.

## Comparison with Alternatives

| Capability | ManageLM | SSH + Scripts | Ansible / Puppet | Generic AI |
|---|---|---|---|---|
| Natural language interface | Yes | No | No | Yes |
| Command allowlisting (hard-enforced) | Yes, in code | No | Limited | No |
| Local LLM (data on-server) | Yes | N/A | N/A | No, cloud only |
| Zero inbound ports | Yes | No (Port 22) | No (SSH) | Varies |
| No learning curve | Yes, just talk | No (Bash) | No (YAML) | Yes |
| Skill-scoped security | Yes | No (full access) | Limited (roles) | No |
| Kernel sandbox (Landlock/seccomp) | Yes | No | No | No |
| Full audit trail | Yes | Manual | Yes | No |
| Multi-tenant RBAC | Yes | No | Limited | No |
| Built-in security audits | Yes, with remediation | No | No | No |
| Compliance frameworks & evidence PDFs | Yes, 8 frameworks | No | No | No |
| Cloud infrastructure connectors | Yes | No | No | No |

## Pricing

### Free Tier (Free Forever)
- $0/month
- Up to 10 agents
- All 33 built-in skills, 396 operations
- Multi-tenant teams & RBAC
- Server groups, scheduled tasks
- Webhooks & API keys
- Full audit trail
- Passkeys & MFA
- Trial LLM included
- Local LLM support
- Security audits, inventory scans, access reports & activity audits
- Cloud inventory connectors & SIEM connectors
- Service monitors, certificate management & encrypted backups
- All plugins included
- No credit card required, no feature gates

### Pro & Enterprise
- Unlimited agents
- Enterprise-grade Pentests
- Priority support
- Custom onboarding
- Volume discounts
- See https://lic.managelm.com/ for plans

## Deployment Options

### ManageLM Cloud (SaaS)
- Managed infrastructure, start in minutes
- Free for up to 10 agents
- Automatic updates
- Trial LLM included
- Sign up: https://app.managelm.com/register

### ManageLM Self-Hosted (Docker)
- Full data sovereignty
- Docker Compose deployment
- Proxied LLM with centralized API keys
- Multi-arch support (amd64 + arm64)
- No external dependencies
- Guide: https://app.managelm.com/doc/docker.html

## Technology Stack

Built on: Anthropic MCP, Claude, Ollama, PostgreSQL, Redis/Valkey, WebAuthn/FIDO2, Ed25519, OAuth 2.0 PKCE, WebSocket, Fastify, TypeScript, Python.

## Company

**RCDevs S.A.**
1 Boulevard du Jazz, 4370 Esch-sur-Alzette, Luxembourg
Email: info@managelm.com
Website: https://www.managelm.com/

## Links

- Website: https://www.managelm.com/
- Portal: https://app.managelm.com/
- Documentation: https://app.managelm.com/doc/
- Quick Start Tutorial: https://app.managelm.com/doc/#quick-start
- Self-Hosted Docker: https://app.managelm.com/doc/docker.html
- Self-Hosted Installer: https://app.managelm.com/doc/package.html
- Plugins: https://www.managelm.com/plugins.html
- Blog: https://www.managelm.com/blog.html
- Blog Posts (JSON): https://www.managelm.com/blog.json
- Pricing: https://lic.managelm.com/
- Terms & Conditions: https://www.managelm.com/terms.html
- Privacy Policy: https://www.managelm.com/terms.html#privacy