ARCOS-Lab Kinematics and Dynamics Library
Simulation harness for Invariant — campaign runners, scenario generators, Isaac Lab dry-run bridge. Part of the unified Invariant workspace at https://github.com/clay-good/invariant.
High-performance agentic robotics framework with ROS2 compatibility
Library for creating, modifying and reading RO-Crates
APIs for controlling a Khepera IV robot.
A utilities library for Rust
Instantaneous Motion Generation for Robots and Machines.
Tiny LLM inference for ESP32 microcontrollers with INT8/INT4 quantization, multi-chip federation, RuVector semantic memory, and SNN-gated energy optimization
A pure Rust framework for embedded nonconvex optimization. Ideal for robotics!
Core library for the aineed AI assistant tool
A generic and parallel implementation of Continuous Conflict-Based Search algorithm for Multi-Agent Path Finding.
Contextual Coherence Fields — earned relational trust for autonomous systems. Patent pending US 63/988,438.
RobotLab is a Ruby framework for building and orchestrating multi-robot LLM workflows. Built on ruby_llm, it provides robots with template-based prompts, tools, and shared memory; networks for coordinating multiple robots with intelligent routing; MCP (Model Context Protocol) integration for external tool servers; and a memory system with Redis backend and semantic caching. Optional gems add Rails integration (robot_lab-rails), durable learning (robot_lab-durable), Ractor concurrency (robot_lab-ractor), and document storage (robot_lab-document_store).
Exposes RobotLab robots and networks as A2A agents over HTTP+SSE. Implements the Agent2Agent Protocol v1.0 (Linux Foundation) via the simple_a2a gem. Supports sync and interactive execution modes, bridging RobotLab's AskUser tool to A2A's input_required/resume lifecycle for multi-turn flows without a terminal dependency.
Provides RobotLab::RactorWorkerPool — a pool of Ruby Ractor workers for executing CPU-bound, Ractor-safe tools in parallel. Includes RactorBoundary (deep-freeze utility for crossing Ractor boundaries), RactorJob/RactorJobError/RobotSpec (frozen data carriers), RactorMemoryProxy (shared Memory access from inside Ractors), and RactorNetworkScheduler (dependency-ordered pipeline across Ractors).
Provides RobotLab::Durable — a YAML-backed knowledge store that lets robot_lab agents accumulate and recall observations across sessions. Includes Entry (immutable value object with confidence scoring), Store (file-locked per-domain persistence), Reflector (end-of-session promoter), and the Learning mixin with RecallKnowledge/RecordKnowledge tools that integrate directly into Robot when robot_lab is present.
Provides Rails Engine, Railtie, ActiveJob base class with Turbo Stream support, persistence models, and generators for using robot_lab in Rails applications.
Provides RobotLab::DocumentStore — a thread-safe, in-memory semantic search store backed by fastembed (BAAI/bge-small-en-v1.5). Store text documents by key and retrieve the closest matches to a natural-language query using cosine similarity. Works standalone or as a drop-in extension for robot_lab agents and networks.
No description provided.
No description provided.
No description provided.
No description provided.