Practical overview
When it fits
Use Loopx when work must continue across sessions or when an agent team needs durable goals, ownership, decisions and evidence rather than isolated conversational runs.
Who it is for
- Developers running long-horizon coding agents
- Researchers managing persistent multi-session agent work
- People coordinating personal agent teams and project decisions
- Builders connecting supported agent runtimes to a durable control layer
Documented uses
- Keep agent goals and project state across sessions, restarts and harnesses
- Track decisions, evidence, tasks and recoverable handoffs
- Coordinate work between personal agents and supported runtimes
- Inspect deliverables, reports and their supporting evidence
Requirements & limits
The project is public, open-source and licensed under Apache-2.0. The documented CLI path requires Python 3.11 or newer and supports self-hosted local use.
- The runtime supplies models and tools; Loopx supplies persistent control, state and coordination.
- The documented workspace supports inspection of goals, tasks, files, schedules, evidence and protected changes.
- The project exposes a CLI and documents a browser/PWA dashboard launch path.
- Integration with named runtimes is described, but the cited material does not provide implementation details or an integration test.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Install Loopx skills for Codex App
Set up the documented Loopx workflow-skills path for a project opened in Codex App.
Before you start
- Python 3.11 or newer
- Codex App
- A project opened in a Codex App thread
Steps
Install or upgrade the Loopx package with the documented Python package command.
Run the documented workflow-skills installation command.
Restart Codex App.
Open a project thread and enter the documented Loopx task invocation.
Expected outcome
Loopx connects the project, plans work as Todos and sets up the documented heartbeat workflow.
Guide limitations
- The cited material presents the walkthrough as a setup and usage path; it does not establish compatibility with every agent host.
- The workspace walkthrough is source-built and does not represent live agent execution.
Compare options for Agent orchestration
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Loopx | Keep agent goals and project state across sessions, restarts and harnesses | CLI, Self-hosted | The project is public, open-source and licensed under Apache-2.0. The documented CLI path requires Python 3.11 or newer and supports self-hosted local use. |
| Agentfm Core | Run a containerized agent in a Podman sandbox on a worker machine | Desktop, Docker, Self-hosted | The README lists desktop installers for macOS and Linux; it says the Windows app is in progress. Its desktop quick start says the bundled node connects to the public mesh. The README notes that the v1 installers are unsigned and macOS may block the first launch. |
| Plano | Route incoming requests to agents based on their declared roles. | Self-hosted, Server | Plano is public source code under the Apache-2.0 license. The README describes hosted Plano models free of charge in the US-central region for a first-run developer experience; for production scale it points to running models locally or contacting the project for API keys. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 2 October 2026
- Original website title
- loopx-project/loopx · Official homepage title · retained in its source language