Back to directory

Dimensional

An agent-native operating system for robotics that lets a developer command humanoids, quadrupeds, drones and other hardware in natural language and build multi-agent systems using camera, lidar and actuator input, without ROS.

Dimensional

Dimensional (dimOS) is an operating system for generalist robotics that lets developers build physical applications entirely in Python, without requiring ROS, and integrates with most robot manufacturers. Agents run as native modules that subscribe to any embedded stream, from perception sources such as lidar and camera and spatial memory down to control loops and motor drivers.

Its capabilities include navigation and mapping with SLAM, dynamic obstacle avoidance and autonomous exploration; perception through object detectors, 3D projections, vision-language models and audio processing; agentic control and an MCP interface for commanding robots in natural language; and spatio-temporal spatial memory with object localization and permanence. Supported hardware spans quadrupeds, humanoids, arms and drones from manufacturers including Unitree, AgileX and DJI, and the project is currently in pre-release beta.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.