Skip to content

Overview

The problem

With LLMs and fast iteration:

  • Bugs discussed in chat are forgotten
  • Tasks stay "mental" but never appear in the team backlog
  • Scattered markdown files (TODO.md, bugs.txt) multiply
  • Nobody knows what is open, in progress, or closed

The solution

Vibeissue connects AI agent chat to GitHub Issues with:

  1. pip install vibeissue — CLI on PyPI (vibeissue, vibeissue-adopt)
  2. Agent instructions — files the LLM reads (AGENTS.md, Cursor rule, Copilot, Claude, …)
  3. GitHub templates — web forms for browser-based issue creation
  4. Skeleton in your repo — labels, tracker config, and rules via adopt

GitHub Issues becomes the source of truth. Local markdown stays for detailed plans and archives — not operational status.

Architecture

You in chat  →  AI agent (reads AGENTS.md)  →  vibeissue CLI  →  GitHub Issues

Requirements for any platform:

  • Python 3 (Windows, macOS, Linux) + pip install vibeissue
  • GITHUB_TOKEN with Issues read/write
  • Repo slug in tracker/github_repo or GITHUB_REPO
  • Agent instructions: run the CLI, don't delegate to the user

Quick path (CLI only)

  1. pip install vibeissue
  2. GitHub token + repo slug in .env
  3. vibeissue list

Optional — full path (AI agents)

  1. Adopt into a project (vibeissue-adopt)
  2. Open the agent and say "Open an issue for…"
  3. Choose your platform