Tiles version 0.4.7 Alpha 11 has been released.
tiles.run/download
Health command upgrade and other QoL improvements. Sync process now exits automatically after syncing. Fixed issues with the initial db connection, and where model downloads did not resume for partial downloads.
A quiet, sincere thank you to our contributors, sponsors, and the broader userandagents.com community for supporting us throughout our alpha-stage journey. ☮︎
Tiles version 0.4.6 Alpha 10 has been released.
tiles.run/download
Adds peer-to-peer device sync, built with @iroh.computer's QUIC networking stack, and encryption at rest for local chats.
Tiles version 0.4.5 Alpha 9 has been released.
tiles.run/download
Adds peer-to-peer device linking for both offline and online networks, built with @iroh.computer, along with bug fixes for the auto-update system.
Tiles version 0.4.4 Alpha 8 has been released.
tiles.run/download
Adds support for a fully offline, portable installer alongside the network installer, with the default gpt-oss-20b model bundled, and daemon process implementation for handling background tasks reliably.
Tiles version 0.4.4 Alpha 8 has been released.
tiles.run/download
Adds support for a fully offline, portable installer alongside the network installer, with the default gpt-oss-20b model bundled, and daemon process implementation for handling background tasks reliably.
Tiles version 0.4.3 Alpha 7 has been released.
tiles.run/download
Turn-based chats with SQLite persistence. Release artifacts now include a .pkg bundle for easier installs. Support for non-Harmony models such as qwen 3.5-4b. Bug fix for venvstack generating multiple tar archives.
Tiles version 0.4.2 Alpha 6 has been released.
New onboarding flow for account and data setup, an OTA updater, and Harmony renderer support for gpt-oss-20b, enabling configurable reasoning effort and improved response quality.
Release notes: www.tiles.run/changelog#0....
Tiles runs local AI.
That means the Python runtime must be deterministic and portable across machines.
With Alpha 4, we now bundle layered venvstacks with pinned dependencies to guarantee reproducible execution.
How it works: www.tiles.run/blog/move-al...
Identity and memory are two sides of the same coin. Tiles makes that coin yours: your user-agent.
We’ve started sponsoring mzau, who’s building MLX Knife, an Ollama-like CLI tool for MLX models on Hugging Face (supports pull, rm, list, show, serve, etc).
github.com/mzau/mlx-knife
Thanks to Tom Dörr for highlighting this project.
The real bottleneck for useful AI isn’t just model quality.
It’s the walls around our data.
A thread on walled gardens, economic incentives, and why even the best models can’t help us if they can’t see us. 🧵
