opentag: a local-first bridge that connects collaboration platforms to local coding agents for governed AI development

What it solves

OpenTag allows teams to integrate local coding agents into their existing collaboration platforms (like Slack, GitHub, or Discord) without moving the conversation to a new tool. It solves the problem of fragmented context by keeping the agent's work loop within the original work thread while ensuring that agent actions are governed, auditable, and executed locally for privacy.

How it works

OpenTag acts as a local bridge between a chat platform and a coding agent. When a user mentions the agent in a thread, OpenTag's local listener captures the request, a dispatcher curates the context, and a local runner executes the task using a coding agent (such as Claude Code or Codex) directly on the user's machine. The agent's proposed changes are sent back to the thread as "action receipts" that a human must approve before they are applied to the system of record.

Who it’s for

Software development teams who want to use AI coding agents within their existing communication workflows while maintaining strict local control over their code and credentials.

Highlights

• Platform Agnostic: Supports Slack, GitHub, GitLab, Lark/Feishu, Telegram, and Discord.
• Local-First Privacy: No cloud service; credentials and agent execution stay on the local machine.
• Executor Neutral: Works with multiple coding agents, including Claude Code and Codex.
• Governed Workflows: Uses a ledger and approval receipts to ensure agent mutations are reviewable and safe.