PhyAgentOS vs rosa

The two are close in size: 2.4k stars for PhyAgentOS, 1.6k for rosa. Over the days we have tracked them PhyAgentOS moved +49.7% and rosa +3%, so PhyAgentOS is growing faster right now.

They split the axes: PhyAgentOS leads on noise control, rosa on model freedom.

Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.

Where they stand today

Provides a session-centered runtime that decouples cognition from physical targets so the same agent workflows run across simulation and real hardware via small target adapters.

Stars
2.4k
Tracked growth
+49.7%
Maturity
Last commit
5d ago
Language
Python
License
MIT
Cost to run
Free, self-hosted; optional external services

Integrates LangChain LLMs with live ROS1/ROS2 systems to let developers inspect, diagnose, and operate robots via natural language.

Stars
1.6k
Tracked growth
+3%
Maturity
Last commit
183d ago
Language
Python
License
Apache-2.0
Cost to run
Your LLM/API key (your usage costs)
0%+50%43 tracked days
PhyAgentOS-Dev/PhyAgentOSnasa-jpl/rosa

Six axes, head to head

Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.

AxisPhyAgentOSrosa
Context depth
How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository.
Workspace-wide context
System-level context
Noise control
How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only.
Multi-layer safety
None mentioned
Customization
How far it bends to your team: custom rules, prompts, style guides, per-path config.
Plugins & configs
Custom agents & prompts
Privacy
Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only.
Self-hostable
Self-hostable
Model freedom
Whether you can point it at any provider, or it is wired to one.
Specific adapters
Bring-your-own LLM
Setup ease
What it takes to get a first useful run out of it.
Easy CLI start
Requires LLM & ROS

Which one to pick

Pick PhyAgentOS if…

Hardware-agnostic — pick PhyAgentOS when you need a self-hostable, auditable runtime that runs identical sessions across sim and real targets with strict multi-layer safety.

  • Noise control: Multi-layer safety (5/5 against 1/5)
Runs in cli. Works with other-fixed.

Pick rosa if…

Robot-focused — use ROSA when you need a customizable, LangChain-based agent that directly interacts with ROS1/ROS2 robot state using your preferred LLM.

  • Model freedom: Bring-your-own LLM (5/5 against 3/5)
Runs in cli. Works with byok.

What people want from each one

Questions people ask

Is PhyAgentOS better than rosa?

They split the axes: PhyAgentOS leads on noise control, rosa on model freedom. PhyAgentOS is worth picking when hardware-agnostic — pick PhyAgentOS when you need a self-hostable, auditable runtime that runs identical sessions across sim and real targets with strict multi-layer safety.

Which of PhyAgentOS and rosa keeps my code private?

PhyAgentOS: Self-hostable (4/5). rosa: Self-hostable (4/5).

What does each one cost to run?

PhyAgentOS: Free, self-hosted; optional external services. rosa: Your LLM/API key (your usage costs).

Full profiles: PhyAgentOS-Dev/PhyAgentOS and nasa-jpl/rosa. Everything else in Robotics & embodied.