Migrating from ClawDeck to KittyClaw
ClawDeck exports to JSON and CSV. KittyClaw imports both. This guide walks you through the move — no data loss, no big-bang migration. Agents are optional; you can run KittyClaw as a plain kanban forever and add automation later.
Step 1 — Export from ClawDeck
- Open your ClawDeck workspace and go to Settings → Export data.
- Choose JSON (full export) — this carries lists, cards, labels, and due dates. Use CSV if you only need the card titles and statuses.
- Save the file locally, e.g.
clawdeck-export.json.
Step 2 — Install KittyClaw
If you haven't set it up yet, clone and start the server:
$cd KittyClaw
$./run.sh # macOS / Linux
$run.bat # Windows
Open http://localhost:5230, create a new project, and point it at any local folder.
KittyClaw scaffolds .agents/ and initialises git if needed.
Step 3 — Import your board
- In KittyClaw, open your project and go to Settings → Import.
- Select your
clawdeck-export.json(or.csv). - KittyClaw maps ClawDeck lists → columns and cards → tickets. Labels and due dates carry over automatically.
- Review the imported tickets. Drag, rename, or split them before doing anything else — nothing is permanent yet.
The whole import takes about two minutes on a typical board. Larger boards (500+ cards) may take a few minutes more.
Step 4 — Configure workflow processing (optional)
Keep using the board manually, or add processing stages that advance tickets toward an outcome. The workflow defines when an agent runs and what happens after its result.
- Choose a pipeline and the column where work should be processed.
- Configure its processor with a mission, relevant skills, and a supported model provider.
- Define acceptance criteria and routes for passing work, corrections, and missing information.
- Add a separate checking stage and any human checkpoint you need.
- Enable processing and place a small ticket in the entry column. Inspect its output and history as it advances.
What KittyClaw adds over ClawDeck
| ClawDeck | KittyClaw |
|---|---|
| Single workspace | Multi-project, isolated SQLite per project |
| Manual card assignment | Column processors execute missions and route outcomes |
| No context across sessions | Processor memory preserves lessons across executions |
| Cloud-hosted, subscription | Self-hosted, AGPL-3.0-or-later — your data stays on your machine |
The kanban muscle memory is identical: drag cards, add labels, comment, assign. Configured stages execute work, check results, and route tickets while preserving the objective and history.