Build notes · Updated September 16, 2026

What is real.
What comes next.

Local AI and your own machine network are available now. The shared network is being built on that foundation. We keep the two separate here.

Available today

Included in the public desktop releases.

Local AI on your hardware: Download a model, load it on your CPU or GPU, and chat locally. No account required for local use.
Your own machine network: In-app pairing, a bundled WireGuard mesh, connection diagnostics, and inference on eligible paired machines with a loaded model.
Persistent memory and tasks: A local memory browser and MCP server for compatible agents, with pinned context and optional read-only memory search across your paired machines.
Desktop 0.1.6: Clearer navigation and machine readiness, relevant context in local chat, credential-pattern redaction, and recovery for interrupted model downloads.
Public installers and updates: Apple Silicon Mac and x86-64 Linux are on 0.1.6. Windows x86-64 remains on 0.1.5. Mac builds are signed and notarized; Windows is unsigned. Checksums are published.

Engineering work and validation still needed before we call it ready.

Contributor reliability: Connect the desktop contribution controls to a supervised contributor, validate real serving across machines, and complete sustained recovery and reconnect testing. This is not in the public 0.1.6 desktop build.
Trusted circles and the open pool: Turn the existing coordinator and routing pieces into reliable, permissioned shared inference. Coordinator dispatch code alone does not make the public network ready.
Intel Mac distribution: Repair the native dependency and packaging path, then validate and notarize an actual Intel build. Intel downloads are paused.
Windows release parity: Build and validate the 0.1.6 update on native Windows hardware. Keep the verified 0.1.5 installer available meanwhile.
Peer access and recovery: Strengthen peer authentication, machine removal, and recovery behavior before extending trust beyond machines you own.

Direction, not a release commitment. There are no promised launch dates.

Contribution accounting: Compute credits tied to useful work, with clear usage accounting and network pricing. Credit earning and redemption are not publicly launched.
Member governance: A staged design for a network its members help govern, distinct from the founder-owned company. Any governance token, structure, or distribution remains subject to review.
Independent security review: An external review of the mesh, coordinator, and privacy boundaries. Do not read internal testing as an independent audit.
More control over shared context: Project-level memory access rules and better retrieval across multiple opted-in machines.
Source publication: Publish application source and licensing details. The app repository is currently private; the downloadable models have their own licenses.
Larger models across machines: Continue evaluating experimental split-model execution, with hardware, bandwidth, and latency limits stated plainly. It is not a general pooled-GPU guarantee.

The installer page always lists the currently published version for each platform.