What if your IDE actually understood the robot you're building?
I described one in plain language and watched it get engineered, in front of me, in a single window.
@pyroscli isn't autocomplete for robotics. It's an IDE that runs the entire robotics engineering pipeline.
It designs the morphology / generates the geometry and inertias / solves and validates the kinematics / sizes the actuators / shows live torque budgets per joint / plans a feasible motion / tunes the controller and simulates.
Every dimension / torque / mass and trajectory comes from deterministic engineering tools with traceable sources not language-model guesses.
In this tour, you'll watch a plain-language spec become a moving robot / the 3D model / the math and the simulation updating together as the pipeline runs.
The goal isn't another URDF that looks correct.
The goal is a robot that's mechanically consistent, mathematically verified, and ready to build without leaving your editor.
Natural language in. Verified robot out.
Pyros V2.0.0 is here.
When we launched Pyros V1, the goal was simple: give robotics engineers an AI agent that could actually work with their robotics stack.
Since then, we’ve been pushing much deeper into the engineering side.
V2 can go beyond generating ROS code.
It can reason about URDFs / kinematics / torque requirements / controllers /motion planning and robot configurations and turn those decisions into actual engineering outputs.
The idea is simple:
Don’t just ask AI to write robotics code / Let it do the engineering.
We’re still early, but V2 is a big step toward the robotics engineering agent we’ve been building toward.
Pyros V2.0.0
getpyros.com/
What if building a robot was as simple as describing it?
I typed a single sentence: "Build a quadruped robot that walks a figure 8."
Everything else was engineered automatically.
@pyroscli doesn't just generate robot code. It executes the entire robotics engineering pipeline.
It designs the robot's morphology / generates the geometry and inertias / solves and validates the kinematics / sizes the actuators / plans a dynamically feasible gait / tunes the controller and runs the simulation.
Every dimension / torque / mass and trajectory comes from deterministic engineering tools with traceable sources not language-model guesses.
In this demo, you'll watch the robot assemble in real time as the engineering pipeline executes, then immediately begin walking a smooth figure-8 trajectory.
The goal isn't to produce another URDF that looks correct.
The goal is to produce a robot that is mechanically consistent, mathematically verified, and ready to build.
Natural language in. Verified robot out.
The wait is finally over.
We’re opening early access for @pyroscli , an AI agent that lets you control and build robots from the terminal.
V1 drops next week | Early users get free access
If you're into robotics or automation , this is for you.
Join the waitlist : getpyros.com





