Search

Low-latency speech-to-speech pipeline

Autonomous agent for task/action planning and execution

Native agent-graph runtime with C++ execution, explicit state patches, resumable checkpoints, and Python bindings.

Installer CLI for Harness Engineering runtime assets

A monitoring system with an agent and a server.

Agent to collect system metrics for Linux machines

A monitoring package with agent and server components

A monitoring system with an agent and a server.

A monitoring system with an agent and a server.

A Lightweight MLOps Framework for Machine Learning Workflows

Tools for applying reinforcement learning on commonroad scenarios.

Unprotected Left Turn for Robust Agents

An Async Online Multi-Agent RL library for training reasoning models on TextArena games.

Create custom reinforcement learning agents with wacky-rl.

Interactive Multi-Agent Reinforcement Learning Environment for the board game Cathedral using PettingZoo

Multi Agent Reinforcement Learning on Trains

Learning Quality Score (LQS) — behavioral evaluation for any RL environment

Multi-Agent Alpha is a robust, open-source framework for building, managing, and deploying intelligent multi-agent systems. It provides a flexible architecture for creating custom agents, with a focus on code quality, testing, and continuous integration.

A reusable foundation for building multi-agent systems with observability, cost tracking, and A2A protocol support

Command-line tool for orchestrating multiple AI agents in parallel or sequence