Robotics & embodied
agents that plan, code and debug for robots and simulators
PhyAgentOS/PhyAgentOS PhyAgentOS is the clear category leader: it focuses on running the same session-centered agent workflows unchanged across simulation and real robots while enforcing multi-layer safety and auditable execution. Before choosing, know whether you need tight ROS-native/edge integration or specialized tooling—PhyAgentOS excels at hardware-agnostic, auditable runtime but many projects specialize in integration, benchmarks, or offline operation that matter for real deployments.
Which one matches your setup?
Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.
Comparison matrix
Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.
| Runs in | Models | Context | Cost to run | |||||
|---|---|---|---|---|---|---|---|---|
⭐ 2.1k +162/7d | CLI | Fixed provider | Workspace & protocols | Multi-layer validation | ●●●●● | Self-hostable | ●●●●● | Free, self-hosted |
⭐ 2.1k +162/7d | CLI | Fixed provider | Workspace-wide context | Multi-layer safety | ●●●●● | Self-hostable | ●●●●● | Free, self-hosted; optional external services |
⭐ 2.1k +162/7d | CLI | Fixed provider | Workspace-wide protocol | Multi-layer safety | ●●●●● | Fully self-hosted | ●●●●● | Free, self-hosted (local compute) |
⭐ 1.4k +14/7d | CLI | BYOKOpenAIAnthropicGemini | Full robot context | Minimal guidance | ●●●●● | Self-hostable | ●●●●● | Depends on external model providers; uses your model client / API key. |
⭐ 154 +11/7d | CLIIDE | BYOK | Tool-only | Sim-safe defaults | ●●●●● | Runs fully local | ●●●●● | Free; local GPU required for some backends/training |
⭐ 775 +9/7d | CLIWeb appCI | BYOKGeminiFixed provider | Diff only | None mentioned | ●●●●● | Self-hostable | ●●●●● | Your API key or local GPU |
⭐ 581 +5/7d | CLI | BYOK | Diff only | None | ●●●●● | Self-hostable | ●●●●● | Open-source, self-hosted; model API costs may apply |
⭐ 367 +9/7d | CLI | Fixed provider | Repo + related files | Isolation & recovery | ●●●●● | Self-hostable | ●●●●● | Self-hosted (hardware/runtime costs) |
⭐ 354 +5/7d | Coding-agent pluginCLIWeb appIDE | BYOKAnthropicFixed provider | Prompt-only context | No noise controls | ●●●●● | Self-hostable | ●●●●● | Free skill files; model/agent API costs may apply |
⭐ 196 +6/7d | CLICIWeb app | OpenAIAnthropicGemini | Diff only | Basic filtering | ●●●●● | Self-hostable | ●●●●● | Free, self-hostable; optional model API costs |
⭐ 138 +4/7d | CLIWeb app | Gemini | Single-script context | No explicit controls | ●●●●● | Cloud API (your key) | ●●●●● | Requires cloud LLM access (your API key). |
⭐ 67 | CLIWeb app | Ollama / localFixed provider | Graph-level context | No explicit controls | ●●●●● | Fully local / offline | ●●●●● | Free — runs locally on your hardware (no cloud required) |
Capability profiles
Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.
Decouples cognition from physical hardware with a session-centered runtime and adapter/bridge architecture that lets the same sessions run unchanged across simulation and real robots while enforcing multi-layer safety and auditable execution.
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.
Decouples cognition from physical hardware with a session-centered runtime and small target adapters so the same agent codebase runs across sim and real robots.
Bridges ROS and the MCP standard to let LLMs fully observe and control robots without modifying robot source code.
Unifies simulation and real hardware under one natural-language Agent API with built-in mesh networking and ROS 2 interoperability, letting the same code run in sim or on robots.
Provides an end-to-end, robotics-focused framework that benchmarks and improves Code-as-Policy agents with interactive robot gym environments, multi-tier benchmarks, a training-free agent, and RL fine-tuning tools bundled together.
A ROS2-native, vendor-agnostic embodied agent framework focused on integrating multi-modal and agentic capabilities directly on robots.
Integrates closed-loop AgentOS, 3D spatial memory, and embodied skills into a unified framework specifically designed for real-robot long-horizon tasks.
All repositories (19)
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…
ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language…
Connect AI models like Claude & GPT with robots using MCP and ROS.
[ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex…
A unified, agentic system for general-purpose robots, enabling multi-modal perception, mapping and localizatio…
Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patte…
Seamlessly integrate state-of-the-art transformer models into robotics stacks
Self-evolving runtime infrastructure for Physical AI and embodied agents. Ground AI agents into robot bodies w…
Control robots and physical hardware with natural language through Strands Agents.
🦾Make your robot autonomous with LLM agent. Set it up with the same ease as normal agents in CrewAI or Autoge…
Advanced MCP Server ROS 2 bridging AI agents straight into robotics
EmbodiedAgents is a fully-loaded ROS2 based framework for creating interactive physical agents that can unders…
A general-purpose robotic agent framework based on LLMs. The LLM can independently reason, plan, and execute a…
Offline fault diagnosis assistant for the AgiBot X2 Ultra humanoid: drop in a log package, get a three-round r…