Overview
SprintiQ Turbo is an open-source sprint planning framework designed to sit on top of Claude Code, Anthropic's AI coding agent. While Claude Code handles code generation, SprintiQ manages what gets built, when, and why — sprint planning, story generation, velocity tracking, and bidirectional sync with the AI agent. It is released under the Apache 2.0 license and can be self-hosted, forked, or extended freely.
What it does
SprintiQ acts as a planning layer that integrates with Claude Code via a CLI tool called sprintiq watch. This creates a live bridge between Claude Code sessions and a sprint board. The system includes:
- Bidirectional sync with Claude Code — changes in the sprint board are reflected in the coding session and vice versa.
- AI-powered user story generation — trained on agile anti-patterns (TAWOS) to produce well-formed stories.
- Sprint planning, capacity management, and velocity tracking — standard agile metrics.
- Persona-aware story generation — stories can be tailored to different user personas.
- Single-user, self-hostable — your data, your infrastructure, your Claude API key.
How to install it (self-hosted)
Prerequisites:
- Node.js 18 or later
- A Supabase project (free tier sufficient for personal use)
- An Anthropic API key (Claude Sonnet 4.6 + Opus)
- A Voyage AI API key (for embeddings)
Setup steps:
- Clone the repository:
git clone https://github.com/SprintiQ-Incorporated/sprintiq.git cd sprintiq- Copy the environment template:
cp env.example .env.local— fill in the required environment variables (see SELF_HOSTING.md) - Install dependencies:
npm install - Push the database schema:
npx supabase db push - Start the dev server:
npm run dev - Create two storage buckets in your Supabase dashboard:
avatars(public) andimages(not public) - Build and link the CLI:
cd packages/cli && npm install && npm run build && npm link - Run the live bridge:
sprintiq watch
Architecture
SprintiQ is built on Next.js App Router, Supabase (auth, Postgres, pgvector), Claude Sonnet 4.6 for generation, and Voyage AI for embeddings. Row-level security (RL