built in 12 hours, we set up a @Tailscale funnel to a local MCP, using: - @AmazonScience Nova Act for the web agent - @cursor_ai CLI and Background Agents SDK - custom memory engine for iMessage indexing to proactively receive messages https://t.co/QohL8fMV07

i built PokeOS for the @interaction challenge with @_rajanagarwal. Poke now - semantically understands and proactively interacts with your iMessages - autonomously interacts with your browser to fill in forms and research - spins up coding agents in your IDE

we built PokeOS. Poke now - interacts with your iMessage proactively - fills forms/searches on your local browser - can write/debug code directly in your IDE

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

i built shadow: a powerful open-source background coding agent with a real-time interface. for async, parallel work on long-running coding tasks! made in a few weeks with @_rajanagarwal @elijahkurien

only in waterloo

We're turning @UWaterloo into a supercomputer 💻 Arceus is a distributed training marketplace for renting unused MacBook compute to a global network, giving developers cheap compute to train large models on consumer hardware clusters! With @_rajanagarwal @josh1yan @simerusm

we're turning @uwaterloo into a supercomputer! arceus is a cross-device distributed compute network for training large models, using model/tensor/pipeline parallelism. you can train anything, from deep neural networks to language models on the network. oss & deployment soon!