Pinned
i haven't started a gpu job by hand in weeks. claude and codex drive them through gpu cli now: grab a gpu across providers, run it, tear it down. great for stateful gpu work
James Lal
@lightsofapollo2
building gpu cli. any command on a cloud gpu, instantly, across providers. here for agents, inference, and getting a gpu when they're all sold out. boulder
- Ready to release beta of attn web - markdown viewing and sharing. staging.attn.sh. Came out of reviewing lots of agent docs (native) and then reviewing my plans with the team (web).
- Seen a few concepts for this already (superlogical.com launching today) and T3. I want some way to coordinate N agents and models across a very large task *from a single session*. Think dynamic workflow + other coding agents/models.
- github.com/gpu-cli/openap… 0.10.0 is out- includes axum (server) support ... For example want to generate anthropic/openapi compat api? easy.
- love rust for coding before and after agentic stuff but now with all these worktrees I am running out of disk space every few days 😬 those target folders add up
