Skip to main content
Vireon Dynamics

Vireon Dynamics · Studio roadmap

One harness today. A stack worth following.

Liminal AI is the product you can install now. Everything else is in development: we name it so you know where we're headed.

Install Liminal AIAll productsLiminal release train

Shipping now

Available today

Beta · v0.1.2

Liminal AI

The fair-source AI agent you run on your own machine. Code, email, documents, research.

Model-agnostic ReAct loop with 500+ tools, persistent memory, persona system, and one-click OAuth connectors. Native desktop app for Windows, macOS, and Linux. FSL-1.1-MIT. Bring your own API key or use Vireon-managed inference. CLI and browser UIs remain for developers.

  • →Native desktop app for Windows, macOS, Linux (primary surface)
  • →One-click connectors: Google, Microsoft 365, GitHub, Slack, Linear, Notion, Xero
  • →Files, shell, git, web, browser, vault, documents, sub-agents
  • →Bring any model, or use managed inference (no key required)
  • →Public alpha on GitHub, moving toward v0.1.0 preview
Explore Liminal AIDocs
Team plan · live

Liminal for Teams

Shared agent infrastructure for teams, not another black-box copilot.

Built on the same harness as Liminal. Team is live today: shared-memory bus per workspace, session audit log, org RBAC, fleet config, and policy governance through Enterprise Edition, plus cloud memory sync across the team.

  • →Hosted shared memory bus, scoped per workspace
  • →Session-event audit log + org RBAC
  • →Fleet config and tool/approval policy governance
  • →Cloud memory sync across the team (Obsidian-compatible)
Explore Liminal for Teams

The Vireon pipeline

What we're building next

Same studio rules: local-first where it matters, model-agnostic, inspectable loops, fair-source when we ship code.

Research

Vireon Bench

CI-grade regression testing for agent harnesses. The eval suite, packaged for teams.

Liminal already ships 20+ scenario packs (`packages/eval`). Vireon Bench would run harness regressions in CI, compare runs over time, and gate releases on agent behavior, not just unit tests.

  • →Scenario packs for memory, tools, web, approvals, long horizon
  • →JSON run sink + pass/fail gates for pipelines
  • →Works against your fork or pinned Liminal release
  • →Open-core aligned with the FSL-1.1-MIT harness
Research

Harness SDK

Embed the Liminal loop in your product. IDE plugin, internal bot, or vertical agent.

For teams building their own surfaces: programmatic access to the same dispatcher, tools, memory bus, and settings model without re-implementing retries, compression, and safety gates.

  • →Headless harness API for custom UIs
  • →Pluggable tool families and lazy loading
  • →Same env / prefs precedence as Liminal
  • →Design-partner program: tell us your integration shape

Shape what we build next

Tell us which product line matters to you. Team, Bench, or SDK.

Ready to run Liminal AI on your machine?

Install free