Discover 3 open source Long Horizon Agents repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Long Horizon Agents projects here are most often combined with AI Agents, Python and Agentic AI. Last updated October 28, 2026.
Uni-Agent is a Python framework for bringing existing agent harnesses into reinforcement learning, with verl integration for training long-horizon agents. It unifies agent tasks and sandbox execution, and collects trajectories for evaluation and training.
ActiveHealth 63/100
LoopX is a local-first semantic control plane and research workbench for long-running agent teams. Its TypeScript core and Python runtime integrations preserve goals, ownership, decisions, and evidence across sessions and agent hosts such as Codex and Claude Code.
NewHealth 83/100
GLM-5 is Z.ai’s open-weight model family for complex systems engineering, coding, and long-horizon agentic tasks. Download model weights or use supported serving frameworks, with model variants designed for different capabilities and efficiency needs.
ActiveHealth 42/100