Embodied Ai Python Packages

cadence-net

A brain that learns from live experience. System 1 by default: perception, memory, plasticity and action. Optional System 2 for self-observation and slow corrections.

mani-skill

Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

rlinf

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

openhire

Job postings with the employer's REAL posting date, pulled from Greenhouse / Lever / Ashby / 北森 Beisen / Moka ATS APIs. MCP server + CLI for Claude, Cursor and any agent. 139 employers in AI infra, autonomous driving 智驾 and embodied AI 具身. Your résumé never leaves your machine.

inspect-robots

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

quackd

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

torchlie

A library for differentiable nonlinear optimization

quackd-lerobot

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

quackd-xlerobot

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

quackd-toddlerbot

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

torchkin

A library for differentiable nonlinear optimization

provael

Provael — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). Prove it. Prevail.

physiclaw

The AI agent that physically operates a phone — the way you do.

quackd-microduck

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

quackd-alohamini

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

quackd-rosbridge

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

quackd-open-duck

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

fieldtrial

Statistically rigorous real-world evaluation for robot policies. Plan how many rollouts you need, run them randomized and blinded from a phone at the robot, let fieldtrial switch LeRobot or openpi policies itself, and get a report that only says "better" when a pre-registered test does.

theseus-ai

A library for differentiable nonlinear optimization

inspect-robots-agent

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

pymaxim

Bio-inspired cognitive architecture for LLM agents providing embodied sensation, homeostatic drives, and brain-modeled persistent memory enable cross-session and cross-context learning without fine-tuning. Works with robots like the Reachy Mini or headless.

mani-skill-nightly

Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

unrealcv

UnrealCV: Connecting Computer Vision to Unreal Engine

embodichain

An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.