Ross ROSS = Recommend OSS · open-source software intelligence for agents

PhyAgentOS/PhyAgentOS-core

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows. observed · 2026-08-28

github.com/PhyAgentOS/PhyAgentOS-core · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

59/100

  • Activity 99
  • Release rhythm 35
  • Longevity 12

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 174
  • days_rel: n/a
  • days_push: 7
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1800 stars · 106 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows, providing a session-centered runtime that decouples cognitive reasoning from physical execution. It supports simulation and real-robot paths, agent verification with failure recovery, and benchmarking of policy loops.

Use cases

  • build embodied AI agents that control robots
  • run agentic workflows for physical task execution
  • benchmark embodied agent policy loops
  • verify agent sessions and recover from failures
  • evaluate agents on Behavior 1K benchmark
  • decouple cognitive planning from physical control in robotics

When to choose

  • you need a runtime for embodied/robotic AI agents with cognitive-physical separation
  • you want built-in agent verification and failure recovery
  • you need benchmarking support for embodied agent policies

When to avoid

  • you only need a chatbot or text-only LLM agent framework
  • you need a production-stable, mature platform
  • you are not working in Python 3.11+

Facets

framework · maturity experimental

agent-framework machine-learning simulation benchmarking sdk artificial-intelligence robotics reinforcement-learning simulation python cross-platform embodied-ai embodied-agent agentic-workflows cognitive-physical-decoupling self-evolving agent-harness session-runtime ai-agents linux

2 sources

Member repositories

RepositoryRoleHealth v2
PhyAgentOS/PhyAgentOS-coremain59

For agents

markdown · JSON · MCP: product_card(name="PhyAgentOS/PhyAgentOS-core")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem