Long Horizon Agents Python Packages

agentglow

Make your AI agents look pretty

loopx

A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

cayu

Cayu is an open-source Python framework for building and running domain-specific long-horizon agents, with a durable runtime built in.

lh-harness

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

lhht

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

ai-agent-persistence

AI agent persistence: evidence-first research on memory, goal continuity, checkpoints, failures, and long-horizon agency in Saient