RobotecAI/rai
RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.
Built on ROS 2, RAI provides modular sub-packages for embodied AI capabilities including speech recognition (rai_asr), text-to-speech (rai_tts), open-set perception (rai_perception), and simulation integration (rai_sim), enabling multi-modal agent architectures without vendor lock-in. The framework abstracts robot embodiment through structured documentation synthesis (whoami tool) and connects to simulation environments and navigation stacks like NoMaD. Demonstrations span manipulation with vision-language grounding, autonomous navigation, and complex reasoning tasks—deployable on real hardware or simulated platforms like Isaac Sim.
458 stars.
Stars
458
Forks
58
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/RobotecAI/rai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
Pipelex/pipelex
Declarative language for composable Al workflows. Devtool for agents and mere humans.
lobehub/lobehub
The ultimate space for work and life — to find, build, and collaborate with agent teammates that...
lemony-ai/cascadeflow
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside...
JetBrains/koog
Koog is a JVM framework for building predictable, fault-tolerant and enterprise-ready AI agents...
strands-agents/sdk-typescript
A model-driven approach to building AI agents in just a few lines of code.