Start Here · 01.02
Agentis Requirements: What You Need Before You Install
Agentis needs Node 20.10+ and pnpm to start — embedded SQLite, a bundled offline embedding model, and zero external services required.
The short answer
Agentis runs as a pnpm monorepo on Node ≥ 20.10. That's the entire hard requirement. It ships with embedded SQLite, a bundled offline ONNX embedding model, and a content-addressed local asset store — so it boots and serves the full Brain (memory formation, semantic recall, knowledge bases) with zero external services and zero API keys. A model runtime is the one thing you attach afterward, and even that has a local option.
What's bundled vs. what you configure
| Component | Default | Override |
|---|---|---|
| Runtime state | ./.agentis (SQLite, secrets, agent homes, backups) | AGENTIS_DATA_DIR |
| HTTP server | 127.0.0.1:3737 | AGENTIS_HTTP_HOST / AGENTIS_HTTP_PORT |
| Embeddings | bundled local ONNX (e5-small), offline | workspace embedding provider config |
| Assets | content-addressed blob store, deduped by SHA-256 | AGENTIS_ASSETS_DIR |
Every row above works out of the box. Nothing in this table requires an account, a credit card, or an internet connection on first boot.
What you'll want to add — and when
Agentis boots complete, but an empty workspace can't think yet. The one thing you attach next is a model runtime: a CLI harness (Claude Code, Codex, Cursor), a local model, or any OpenAI-compatible HTTP endpoint. Everything else below is genuinely optional, added only when you need it:
| You want to… | Then attach |
|---|---|
| Give an agent a model to think with | One CLI harness or HTTP endpoint — see Bootstrap Your First Agent |
| Reach WhatsApp, Slack, Telegram, or email | A channel connection — see Reach |
| Generate images, audio, or video | A media provider key — see The Agent-Native SDK |
| Export traces to an observability backend | AGENTIS_OTEL_ENDPOINT — falls back to a no-op tracer if unset |
Storage and platform notes
SQLite is single-writer by design — this is an intentional choice for a local-first, single-tenant operator deployment, not a scaling shortcut you'll hit later. Plan disk space around two things that grow over time: the SQLite database itself, and the content-addressed asset store under AGENTIS_ASSETS_DIR, which holds every image, document, and generated artifact your agents produce (deduplicated, so re-generating the same output twice costs nothing extra).
Agentis runs on Windows, macOS, and Linux. The examples throughout these docs use POSIX shell syntax; swap in the PowerShell equivalent if that's your environment.
Continue
Agentis is local-first infrastructure for AI agents that keep their memory, identity, and skills for life — even when you swap the model underneath them.
Clone the repo, run pnpm install, and start the Agentis API on 127.0.0.1:3737 — then open the dashboard and mint your first API key.