Export the weekly usage report as CSV.
waiting for a free slot (3 agents at most)
Notes & moderation
Screened for spam and personal data before an agent can read it.
Software factory by Catchscript
Catchscript is a kanban software factory that connects all your agents. Drag an issue or a piece of user feedback into Todo, and an agent investigates, plans, builds, and opens a pull request. You approve the plan and decide what merges.
The problem
Each agent session lives in one person's terminal, so work is hard to share, queue, or hand over.
Why a change was made, who approved the plan, and which checks ran are scattered across chats and logs.
Agent usage windows run out, and nobody sees it until an agent stalls.
Feedback and issues arrive in New. Drag a card into Todo to start an agent. Three agents run at most; the rest wait for a free slot.
Drag a card into Todo, or change its status, to start an agent.
Export the weekly usage report as CSV.
waiting for a free slot (3 agents at most)
Screened for spam and personal data before an agent can read it.
Reset time shows UTC instead of my local time.
waiting for a free slot (3 agents at most)
Screened for spam and personal data before an agent can read it.
Thanks for building this.
waiting for a free slot (3 agents at most)
Screened for spam and personal data before an agent can read it.
Could the menu-bar popover follow dark mode?
waiting for a free slot (3 agents at most)
Screened for spam and personal data before an agent can read it.
Nothing here
Codex quota window disappears after re-login.
waiting for a free slot (3 agents at most)
Screened for spam and personal data before an agent can read it.
Warn me before the five-hour window runs out.
waiting for a free slot (3 agents at most)
Screened for spam and personal data before an agent can read it.
Nothing here
Define your lifecycle stages, then set rules for each stage and each type of work.
Issues, pull requests, and user feedback land on one board.
Open the Intake stage →Agents investigate each card, gather context, and say what is missing.
Open the Triage stage →The investigation becomes a plan you can read, edit, and approve.
Open the Planning stage →An agent implements the approved plan and runs your checks.
Open the Building stage →A separate agent reviews the pull request before you decide.
Open the Review stage →Verified work closes, and the source hears back.
Open the Done stage →The rules every card follows, whichever agent does the work.
When a card enters Todo, an agent reads the codebase, gathers context, and writes an implementation plan.
A person reviews and approves the plan. Nothing is built without that approval.
The agent implements the approved plan on its own branch, runs the checks, and opens a pull request.
When review feedback arrives, the agent revises the change and runs the checks again.
Starting work, approving the plan, and accepting the review each wait for a person.
The final merge is always a human decision on GitHub.
Team
Product
A kanban board where each card carries its own agent session, files, and history.
Connected agent sessions, such as Claude Code and Codex, that investigate, plan, build, and review in isolated worktrees.
Provider limits and reset times decide when an agent can start, across all your accounts.
Tool calls, diffs, checks, and decisions, recorded on the card that caused them.
Solutions
User comments go to a feedback board. The good ones become pull requests.
Agents reproduce the bug before anyone writes a plan.
Dependency upgrades, flaky tests, and cleanup, one approved plan at a time.
One owner per board, with GitHub as the place teammates review.
A software factory automates parts of the development lifecycle with agents. Catchscript uses staged automation: explicit gates at intake, planning, and review keep each change measurable and reversible.
Any coding agent you connect, starting with Claude Code and OpenAI Codex, signed in with your own accounts. Model usage stays under your provider plans and their limits.
No. Agents open pull requests. A person approves every plan and makes every merge decision.
Yes. Connect an existing GitHub repository. Agents read the code, follow your checks, and work on separate branches.
Catchscript, a Korean AI company founded in May 2026.
Catchscript is in early access by invitation and is not publicly released yet.
Take work from feedback to a reviewed pull request, with agents you govern.