Roadmap

Where Stallari is going

An honest, phase-based view of what's been built, what's in progress, and where the platform is headed.

Built in Swift for macOS. Local-first. Markdown-native.

Beta underway — early access opening late May.

Phase 1–3

Foundation

Shipped

Swift harness, vault engine, dispatch engine, provider abstraction, trace store.

Phase 4

Intelligence layer

Shipped

Agent memory with importance decay, recall, and consolidation. Post-dispatch memory pipeline.

Phase 5

Native interfaces

Shipped

macOS app — published, notarised, Developer ID signed. Setup wizard, fleet sidebar, digest views, plugin management, and privacy controls.

  • Setup wizard with 9-step onboarding and vault detection
  • Marketplace browser with service, tier, and category filters
  • Privacy controls with content redaction and domain-scoped exclusions
  • Secure Enclave credential store for providers and tools
  • Self-upgrade via GitHub Releases
Phase 6

Multi-device

Shipped

Run Stallari across macOS devices in a fleet with automatic leader election and health monitoring.

  • Discover peers automatically via Tailscale or Bonjour
  • Enrol devices with QR scan and optional 2FA — per-peer tokens, individually revocable
  • Three-tier leader election with automatic dispatch failover
  • Fleet health monitoring with anomaly detection
  • Interactive fleet topology visualisation
  • Browse agent traces and coordinate dispatch across your fleet
Phase 7

Productisation

Shipped

Plugin marketplace, commerce, identity, and distribution. 20+ Blade MCPs available — including community contributions for Home Assistant, Shopify, Xero, Gmail, iMessage, Cloudflare, and more.

  • Marketplace with conformance tiers — tools (MCPs) and Packs (bundled agent workflows)
  • Organisation packs — teams share private packs scoped to their org
  • Developer ID signed and notarised — installs clean on macOS
  • In-app self-updates and binary distribution via GitHub Releases
  • Marketplace sign-in (GitHub and Apple) with Paddle checkout and licensing
  • Built-in OIDC identity provider with seat-based licensing
  • Opt-in crash reporting with PII scrubbing, health probes, and process guardian
Phase 8

Networking and service mesh

Shipped

Zero-config secure networking between your tools and devices. Automatic HTTPS, cryptographic request signing, and cross-machine trace sync.

  • Cryptographically signed service-to-service requests
  • Local LLM access via LM Studio over your private network
  • Reliable trace sync across machines
  • Unified networking settings UI
Phase 9

Embedded dispatch engine

Active

Your agents, your providers, your rules. Run workflows across Anthropic, xAI, OpenAI, Google, LM Studio, and on-device Apple Silicon models — mixing providers within a single workflow. Pack-driven orchestration means workflows are portable YAML, not vendor lock-in. Scope-based routing ensures the right agent handles the right work.

  • Run workflows on xAI (Grok), Anthropic (Opus), OpenAI (GPT), Google (Gemini), LM Studio, or MLX Swift and Apple Foundation on-device models — mix providers within a single workflow
  • Pack-driven orchestration — define agent workflows as portable YAML manifests
  • Webhook-triggered dispatch — inbound events from GitHub, Xero, Home Assistant auto-wire into workflows
  • Chat interface with conversation persistence and multi-provider backends
  • Intelligent email routing — classify inbound mail by domain scope, with a correction loop that learns your preferences
  • Local GPU worker — offload inference to your own hardware across platforms
  • Streaming tool-use in embedded backends
  • MLX Swift — run local models natively on Apple Silicon (Nemotron, Qwen, Phi-4, Llama)
  • ISO 42001 compliance posture
Phase 10

Open Memory

Horizon

Your intelligence is yours. Full-fidelity export of every memory, association, and learning your agents have built — in open formats, with documented schemas, importable anywhere.

  • One-command memory export — Markdown, JSON, or SQLite, with full association graph
  • Documented memory schema — published spec so other tools can read your memories
  • Memory import — bring learnings from other systems into Stallari
  • Association graph visualisation — explore what your agents have learned and how concepts connect
  • Memory portability guarantee — if you leave, your intelligence leaves with you
Phase 11

Federation and beyond

Planned

Extend beyond your own fleet. Organisation members expose selected services to each other, each running their own choice of mesh — Tailscale, Nebula, or NetBird.

  • Fabric transport layer — federate between Tailscale, Nebula, and NetBird across organisational boundaries
  • Cloudflare Tunnel with BYO domain — expose services without a traditional VPN
  • Pulse service mesh — real-time communication across your fleet with org-scoped group chat
  • Multi-vault support
  • Inter-user coordination protocols

Want to follow along?

You're on the list. We'll be in touch.

Something went wrong. Try again or email [email protected].