Had dinner with a friend last night.
She kept listing all these amazing places in London she'd been to. I hadn't been to a single one.
She said: "You're missing out on life."
I said: "You're missing out on AI."
If you're also tired of reading AI slop in every agent response, highly recommend using the @excalidraw MCP.
Much faster to understand any architecture or data flow. ASCII and Mermaid diagrams get hard to read fast.
Don't explain it, just draw it.
Your agent's Jev decisions are now visible in Laminar.
Initialize once, and every system_one call from @typesafeai's SDK becomes a span: state in, typed answers out, token counts and prices included. Python and TypeScript, direct or via OpenRouter.
Congrats to the Laminar team on their raise! It has been excellent working with them so far on profiling and improving agent skills.
More and more love for the open agent toolstack ❤️
Excited to share that @lmnrai has raised $3M to build open-source observability for long-running AI agents.
Laminar is how companies like @browser_use, @OpenHandsDev, and Rye see what their agents are doing, understand why they fail, and spot patterns across millions of runs.