Your AI. Your hardware.
Your data.
Local AI without the config files. Pyre installs in one step, picks the right model for your machine, and gives you memory (Engram) and personality (Persona) that follow you across conversations. Pro adds end-to-end encrypted sync across every device you own.
Your AI. Your data. Your machine.
Local-first isn't a marketing phrase. Pyre runs models on your GPU, stores personal memory on your disk, and treats every cloud provider as optional. You decide what leaves the machine.
Your data never leaves
Pyre runs on your hardware. Conversations, personal memory, and personality stay on disk in your home directory. Want to use a cloud model? Bring your own key — Pyre never proxies your traffic through us.
No telemetry tax
No hidden phone-home, no usage tracking, no "anonymous analytics." Crash logs stay local. Open the source if you want to verify.
BYO cloud key
Switch between local models and any cloud provider on a per-conversation basis. OpenAI, Anthropic, OpenRouter — your account, your bill, your audit trail.
End-to-end encrypted sync
Pro tier sync uses end-to-end encryption. Your devices hold the keys; OneNomad never sees plaintext. Backups are E2E too.
Your AI grows with you, across every device.
Most chat tools have zero per-user state — every conversation starts from blank. Pyre's design encourages compounding investment: the more you use it, the more it's yours. Switching costs grow with time, by design.
Personality persists
Persona evolves with use — Plutchik emotion tags, Big Five traits, behavioral signals. Your AI sounds the same on Tuesday as it did on Monday, on your laptop as on your desktop. The voice is yours.
Personal memory accumulates
Engram remembers conversations, decisions, and project context. Hybrid search (vectors + keywords + recency) returns the right slice for the prompt at hand. 92% R@10 on LoCoMo today.
Agents keep working
Pro adds an always-on background runner. Long agent sessions continue when your laptop sleeps. Pick up the thread on any device, scheduled or on-demand.
Free locally.
Pay for continuity.
Open-core funnel: free local runtime → paid cloud features → enterprise contracts. Same product, three deployment shapes.
- Full local runtime — every model, every provider
- Single-machine personal memory (Engram) + personality (Persona)
- Multi-agent orchestration up to your hardware limit
- Desktop · CLI · Web server · Chrome companion
- Local cognitive stack — 200K effective context on 16 GB GPU
- Everything in Core
- Your Persona, personal memory, and project context follow you across every device — E2E encrypted
- Always-on background agents — long sessions keep running when your laptop sleeps
- Nightly E2E-encrypted backups — restore your AI on any new machine in minutes
- Full memory portability — export your Persona and Engram any time. Your data, your call.
- Curated plugin & SKILL.md catalog
- Everything in Pro
- On-prem deployment — Terraform module, Helm chart, air-gap installer
- SSO / SAML — Okta, Azure AD, Google Workspace
- Audit logging, RBAC, configurable retention
- Cortex Enterprise — managed company-memory ingestion
- 99.9% SLA + implementation services
One command. Any machine.
Pyre auto-detects your hardware on first launch — CPU, Mac Metal, CUDA, ROCm, or Vulkan — and picks a model that fits. No config files, no ceremony.
# macOS / Linux
curl -fsSL https://getpyre.dev/install.sh | sh
# Or via npm
npm install -g @onenomad/pyre
# Run
pyre start