Toolbox/Applied agents

Robotics & embodied

agents that plan, code and debug for robots and simulators

19 repositories, most starred first
State of the category

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.

ROS & runtime integration
Teams often need native, low-friction ways to connect LLM-driven agents to existing ROS1/ROS2 stacks and robot runtimes without rewriting robot code, so bridges and ROS-native frameworks keep appearing.
Safety & audibility
Physical systems require fail-closed execution, evidence-bearing receipts, and production-grade testing to operate safely in the real world, driving projects that focus on auditable and secure execution layers.
Benchmarks & training pipelines
Teams building more capable embodied agents need standardized benchmarks, sim environments, and tooling for evaluation and RL/fine-tuning, so end-to-end training and benchmark frameworks are common.
Local / offline & edge
Many deployments must run fully local or offline for latency, reliability, or privacy reasons, prompting projects that package local multimodal models and edge-friendly runtimes.
Turnkey GUIs & robot-specific stacks
Teams doing rapid experiments or working with specific robot platforms value out-of-the-box stacks, GUIs, and preconfigured integrations that reduce setup time and hardware-specific engineering.
Find your fit

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.

Where should reviews happen?
Can code leave your infrastructure?
What matters most?
Model access?
Pick at least one answer to get a shortlist.
Side by side

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 inModelsContextCost to run
2.1k +162/7d
CLIFixed providerWorkspace & protocolsMulti-layer validationSelf-hostableFree, self-hosted
2.1k +162/7d
CLIFixed providerWorkspace-wide contextMulti-layer safetySelf-hostableFree, self-hosted; optional external services
2.1k +162/7d
CLIFixed providerWorkspace-wide protocolMulti-layer safetyFully self-hostedFree, self-hosted (local compute)
1.4k +14/7d
CLIBYOKOpenAIAnthropicGeminiFull robot contextMinimal guidanceSelf-hostableDepends on external model providers; uses your model client / API key.
154 +11/7d
CLIIDEBYOKTool-onlySim-safe defaultsRuns fully localFree; local GPU required for some backends/training
775 +9/7d
CLIWeb appCIBYOKGeminiFixed providerDiff onlyNone mentionedSelf-hostableYour API key or local GPU
581 +5/7d
CLIBYOKDiff onlyNoneSelf-hostableOpen-source, self-hosted; model API costs may apply
367 +9/7d
CLIFixed providerRepo + related filesIsolation & recoverySelf-hostableSelf-hosted (hardware/runtime costs)
354 +5/7d
Coding-agent pluginCLIWeb appIDEBYOKAnthropicFixed providerPrompt-only contextNo noise controlsSelf-hostableFree skill files; model/agent API costs may apply
196 +6/7d
CLICIWeb appOpenAIAnthropicGeminiDiff onlyBasic filteringSelf-hostableFree, self-hostable; optional model API costs
138 +4/7d
CLIWeb appGeminiSingle-script contextNo explicit controlsCloud API (your key)Requires cloud LLM access (your API key).
67
CLIWeb appOllama / localFixed providerGraph-level contextNo explicit controlsFully local / offlineFree — runs locally on your hardware (no cloud required)
Ranked by maturity — 6 more in the full catalog below.
At a glance

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.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

Bridges ROS and the MCP standard to let LLMs fully observe and control robots without modifying robot source code.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

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.

ContextNoiseCustomPrivacyModelsMaturity

A ROS2-native, vendor-agnostic embodied agent framework focused on integrating multi-modal and agentic capabilities directly on robots.

ContextNoiseCustomPrivacyModelsMaturity

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…

2.1k
+1627d
Python
6 mo

PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…

2.1k
+1627d
Python
6 mo

PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…

2.1k
+1627d
Python
6 mo

PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursi…

2.1k
Python
6 mo

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language…

1.6k
+47d
Python
2 yrs

Connect AI models like Claude & GPT with robots using MCP and ROS.

1.4k
+147d
Python
1 yr

[ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

775
+97d
Python
5 mo

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex…

581
+57d
Python
2 yrs

A unified, agentic system for general-purpose robots, enabling multi-modal perception, mapping and localizatio…

367
+97d
Python
10 mo

Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patte…

354
+57d
Python
6 mo

Seamlessly integrate state-of-the-art transformer models into robotics stacks

298
Python
2 yrs

Self-evolving runtime infrastructure for Physical AI and embodied agents. Ground AI agents into robot bodies w…

196
+67d
Python
5 mo

Control robots and physical hardware with natural language through Strands Agents.

154
+117d
Python
6 mo

🦾Make your robot autonomous with LLM agent. Set it up with the same ease as normal agents in CrewAI or Autoge…

138
+47d
Python
11 mo

Advanced MCP Server ROS 2 bridging AI agents straight into robotics

86
Python
1 yr

A simple MCP server for the SO-ARM100 control

83
Python
1 yr

EmbodiedAgents is a fully-loaded ROS2 based framework for creating interactive physical agents that can unders…

67
Python
3 yrs

A general-purpose robotic agent framework based on LLMs. The LLM can independently reason, plan, and execute a…

24
+27d
Python
9 mo

Offline fault diagnosis assistant for the AgiBot X2 Ultra humanoid: drop in a log package, get a three-round r…

22
Python
3 mo

More in Applied agents