Practical overview
When it fits
Use OpenTag when a team wants Slack to be the request and status conversation while agent execution stays on a paired, user-controlled computer. An offline Runner leaves work visibly queued until it is ready.
Who it is for
- Engineering teams that want to request coding work from Slack.
- Teams that want coding agents to run on a computer they control against local checkouts.
- Operators able to host a control plane and pair a Runner.
Documented uses
- Queue coding work by mentioning OpenTag in a Slack thread.
- Run an ACP-compatible coding agent against the Runner’s local checkout.
- Return work status, decisions and evidence to the originating thread.
- Optionally publish a governed GitHub draft pull request and report publication evidence.
Requirements & limits
The documented deployment is self-hosted. The repository identifies the software as MIT-licensed.
- The control plane needs Docker Compose, PostgreSQL and a public HTTPS origin reachable by Slack.
- The described workflow pairs one Runner with the self-hosted control plane and has no standalone local mode.
- Slack is the supported request inbox in the documented team profile; GitHub is a project target and optional publication and evidence provider.
- Draft pull-request publication is a distinct governed stage; OpenTag does not automatically merge.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up the self-hosted control plane and pair a Runner
Start OpenTag’s self-hosted presence and pair one computer as the Runner.
Before you start
- Docker Compose
- PostgreSQL through the included Compose profile
- A public HTTPS origin reachable by Slack
- A trusted control-plane URL and bootstrap pairing credential
- Slack and relay-content secrets configured as files
Steps
Clone the OpenTag repository, enter deploy/compose, copy .env.example to .env, replace its placeholders and create the documented file-backed secrets.
Start the control plane with Docker Compose using the configured environment file.
Install the OpenTag CLI, run setup with the control-plane relay URL, and start the Runner; configure its GitHub Project Target and ACP executor during pairing.
Run opentag doctor and opentag status to inspect the installation before making a real request.
Expected outcome
A self-hosted control plane is running and one Runner is paired for the configured project target and ACP executor.
Guide limitations
- The paired Runner requires the self-hosted control plane and has no standalone local mode.
- The setup instructions require entering the exact project-target ID used by the active Slack binding.
- The guide documents setup and status checks, not a verified execution result.
Compare options for AI coding assistance
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 |
|---|---|---|---|
| Opentag | Queue coding work by mentioning OpenTag in a Slack thread. | Linux, macOS, Self-hosted, Server | The documented deployment is self-hosted. The repository identifies the software as MIT-licensed. |
| Llmcode | Inspect a project's directory structure with `/tree`. | CLI | The documented setup requires an API key and supports an API base URL and model setting. The project is open source under Apache-2.0. |
| Klaat Code | Open a project directory for terminal-based coding assistance. | CLI, Server | The README provides a global npm installation command and documents browser sign-in with a KlaatAI account. It also identifies the repository as open source under Apache 2.0. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 11 October 2026
- Original website title
- amplifthq/opentag · Official homepage title · retained in its source language