# gadak

> Your team's Jira — and its Confluence wiki — mirrored into one local SQLite
> file. Reads are local SQL and land in milliseconds; writes go through Jira,
> which stays the source of truth. Built agent-first: a CLI, an MCP server,
> and a documented schema agents query directly. No outbound telemetry.

For an agent working with a human's Jira: install gadak, run `gadak sync`,
then read the mirror with `gadak sql` (or the MCP tools). The promised query
surface is the `issues_full` view plus the recipes in AGENTS.md. Keep status,
priority and issue type off display names — use `status_category`,
`priority_rank`, `issue_type_id`.

## Docs

- [README](https://github.com/midagedev/gadak/blob/main/README.md): what it is, quick start
- [Agent setup](https://github.com/midagedev/gadak/blob/main/docs/AGENT_SETUP.md): `gadak skill install` for shell agents, `gadak mcp install` for MCP clients
- [Schema & query recipes](https://github.com/midagedev/gadak/blob/main/AGENTS.md): `issues_full`, the query contract, worked SQL examples
- [Concept](https://github.com/midagedev/gadak/blob/main/docs/CONCEPT.md): mirror-is-a-cache model, what persists where
- [Benchmarks](https://github.com/midagedev/gadak/blob/main/docs/BENCHMARKS.md): method and measurements against Jira REST
- [Install](https://github.com/midagedev/gadak/blob/main/docs/INSTALL.md): all platforms
- [Security](https://github.com/midagedev/gadak/blob/main/SECURITY.md): exactly where bytes go

## Try

- [Live demo](https://gadak.dev/demo/): the real UI over a scrubbed 534-issue sample mirror
- [Public backlog](https://gadak.dev/backlog/): gadak's own issues, served by gadak
- [Source](https://github.com/midagedev/gadak): Go + Svelte, Apache-2.0

## Install

- macOS app (CLI included): `brew install --cask midagedev/tap/gadak`
- CLI only (macOS, Linux): `brew install midagedev/tap/gadak-cli`