Plans
The free tier is a complete personal AI assistant — unlimited memory, full safety, all runners. Pro unlocks the full autonomous daemon with multi-channel, advanced security, and managed infrastructure.
Free vs Pro
Both tiers run the same binary on your machine. You bring your own API keys. The difference is what the software unlocks.
| Free | Pro — $9/month | |
|---|---|---|
| Core AI | ||
| AI / Inference ― BYOK | Unlimited | Unlimited |
| Memory ― all types, hybrid retrieval, consolidation | Unlimited | Unlimited |
| Runners ― Agent , Loop , Coder | All 3 | All 3 |
| Scheduler, search, plugins | Full | Full |
| Safety & Security | ||
| LLM Judge (4 risk levels, escalation) | Full | Full |
| Secret & credential leak detection | Coming soon | Coming soon |
| PII redaction | Full (local) | Full (local) |
| Prompt injection scanning | Essential (static rules) | Advanced ― and frequently updated |
| Channels & Delivery | ||
| Desktop app | Always available | Always available |
| External channels (Telegram, WhatsApp, Slack, iMessage, Discord, and more) | 1 active at a time | Unlimited simultaneous |
| Cross-channel memory continuity | Desktop ↔ 1 channel | All channels seamlessly |
| Delivery | Basic (respond on same channel) | Presence-aware, quiet hours, proactive agent, cascade |
| Infrastructure | ||
| Managed remote access | DIY | Zero-config managed remote access |
| Licence | ||
| Commercial use | Personal only | Permitted |
Free — $0 forever
Download Salmex I/O and run it on your own machine. Unlimited memory, full agentic capabilities, the LLM judge, scheduler, search, and plugins. Desktop chat is always available. Pick one external channel — Telegram, WhatsApp, Slack, Discord, iMessage, or any other supported channel. Switch anytime, but only one active at a time. Free for personal, non-commercial use. No time limit. No trial.
Pro — $9/month, billed annually
The full autonomous daemon. Unlimited simultaneous channels with cross-channel memory continuity. Managed remote access — one command, zero config, no ngrok or Cloudflare setup. Advanced prompt injection scanning with cloud-updated rules and weekly updates. Presence-aware delivery with quiet hours, proactive agent, digests, and smart routing. Commercial use licence. 30-day money-back guarantee.
Infrastructure plans
For users who want always-on, managed hardware. Both include everything in Pro.
| CPU — $99/month | GPU — $249/month | |
|---|---|---|
| Everything in Pro | ✓ | ✓ |
| Dedicated physical server (not a VM) | ✓ | ✓ |
| Always on — no uptime worries | ✓ | ✓ |
| Managed infrastructure & automatic updates | ✓ | ✓ |
| Daily backups | ✓ | ✓ |
| Full SSH read access | ✓ | ✓ |
| Full transparency (inspect the source code) | ✓ | ✓ |
| Dedicated GPU | — | ✓ |
| On-device AI (no external API needed) | — | ✓ |
| Zero data leaves server | — | ✓ |
| No API keys required | — | ✓ |
CPU — $99/month
A dedicated physical server, managed entirely by us. Always on, always reachable. You bring your own AI provider keys and we handle everything else — setup, updates, backups, security, and monitoring. Connect from the Salmex I/O app or reach your agent from any connected channel.
GPU — $249/month
Everything in the CPU plan, plus a dedicated GPU. Run AI models directly on the server via Ollama — no external API calls, no data leaves your server, no API keys needed. The most private and self-contained option.