The next generation of physical intelligence will not be built in simulation.
Stord Labs is our physical intelligence lab at our Atlanta HQ where we develop and deploy AI and agentic robotics that scale across nearly 100 facilities on a single unified stack. Applying cutting edge technology to real world outcomes.
The physical intelligence era for commerce is here.
@dinasaur_404 nice! will there be any type of event for when cloudflare fails to deliver a static asset due to an "infrastructure routing issue" in a specific region? happy to provide more context if interested :)
Introducing Mirage, a unified virtual filesystem for AI agents!
6 weeks. 1.1M+ lines of code. We rewrote bash from the ground up so cat, grep, head, and pipes work across heterogeneous services. S3, Google Drive, Slack, Gmail, GitHub, Linear, Notion, Postgres, MongoDB, SSH, and more, all mounted side-by-side as one filesystem.
Bash that AI agents already know works on every format! cat, grep, head, and wc parse .parquet, .csv, .json, .h5, even .wav! One pipe can stitch S3, Drive, GitHub, Slack, and Linear together, same Unix semantics throughout.
Workspaces are versioned too. Snapshot, clone, and roll back the whole thing with one API call. A two-layer cache turns repeated reads into local lookups, so agent loops stay fast and cheap.
Drop a Workspace into FastAPI, Express, or a browser app. Wire it into OpenAI Agents SDK, Vercel AI SDK, LangChain, Mastra, or Pi. Run it alongside Claude Code and Codex.
Site: https://t.co/zo1orc2wA9
GitHub: https://t.co/zeRAKri7I9
#AIAgents #OpenSource #AgenticAI #Strukto #Filesystem #VFS
@elithrar@Cloudflare Awesome π. I think once the picture clears up a bit for querying data it'll be π―. There is a bit of ceremony at the moment for reading from r2 iceberg tables (e.g. using google colab + duckdb to connect to r2 iceberg)
are you a fan of @CloudflareDev and the entire Workers AI & general workers platform? we are actively hiring to build on the primitives. as of today, we use every single workers product in production and are continuing to invest in it. so if you're pumped about agents week, come and party with us! (and also laugh at us being that things we built just got shipped officially this week π)
and note: if you're seriously interested, i'd be happy to jump on a brief call before going through the formalized process. just send a dm with github/linkedin references.
https://t.co/OaP2TvTT8L
sent this to the team today
everything great comes from being able to delay gratification for as long as possible
and it feels like we're collectively losing our ability to do that
@threepointone makes sense. sent you a message on discord, but chose to do this in my impl for specific calls with an additional .emit in an observability middleware