LongHorizon
LongHorizon is an agent app that keeps AI agents working on long desktop and terminal tasks until results are verified for developers.
What it is good for
- Keeping a long desktop task on track across many steps
- Checking that an agent's finished work actually meets the goal
- Resuming an interrupted multi-step task without starting over
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- Claude Code, Codex, OpenCode, OpenClaw
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 1,813
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is LongHorizon free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use LongHorizon?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does LongHorizon work with?
- According to its own documentation, it works with Claude Code, Codex, OpenCode, and OpenClaw.
- What is LongHorizon good for?
- Keeping a long desktop task on track across many steps, checking that an agent's finished work actually meets the goal, and resuming an interrupted multi-step task without starting over.
Similar agents
- Atomic Agent
Atomic Agent is a local-first agent app that runs on your own machine to browse the web, edit files, and run approved commands for people who want to keep their data local.
- AlphaCode
AlphaCode is an agent app that writes, edits, and tests code from your terminal for developers, with a free built-in model.
- Dodaios
Dodaios is an open-source desktop app that runs coding agents, browser tasks and apps by voice or chat on your own machine for developers and power users.
- Celesto
Celesto is a secure, persistent virtual computer that gives AI agents their own desktop for running code and browsing for developers.
- Eido
Eido is an agent app that helps developers describe a coding task, let an AI agent make changes, and review them in a macOS code editor.
- rtk
rtk is a command-line proxy that shrinks the output of developer commands before an AI coding agent reads it, to cut token costs.