Self-hosted · AI-native · in development

Death to kanban.
A command center
for your AI agents.

Daikonbun is a task board that runs itself. Drop in a rough task; a pipeline of AI agents refines, plans, reviews, builds, and verifies it — moving the card across the board and pausing for you only at the gates that matter.


The wedge

Boards track work. Agents do work. Nothing runs the process between them.

Kanban boards
Track work, but never do it.
Trello, Jira, Linear — beautiful columns that wait for a human to move every card.
AI coding agents
Do work, with no process.
Powerful, but no durable, multi-stage, reviewable pipeline around what they produce.
Daikonbun
The process layer for AI-assisted work.
Opinionated stages, explicit review gates, a durable signed record, and a human in the loop by default.
The pipeline

Every card walks the line — and stops for you at the gates.

A card moves left to right through typed stages. Each stage is worked by a specialized agent role; each review gate produces a verdict and a score. Approve to advance, or send it back.

01 · Intake
Refiner

Refine

Turns a rough note into a clear task with acceptance criteria.

02 · Plan
Planner

Plan

Writes the implementation plan and decision log.

03 · Gate
Plan Reviewer

Review plan

Scores the plan. You confirm — or it loops back.

04 · Build
Builder + Test Author

Build

Implements the change and writes the tests to hold it.

05 · Gate
Code Reviewer

Review code

Reviews the diff for correctness and quality.

06 · Test
Verifier / CI

Verify

Runs the full suite. Green ships; red loops back.

07 · Done

Done

Merged, with the whole story on the card.

Conductor orchestrates the loop — dispatching each role, evaluating gates, and driving the card to done. You watch from the command center.
Design tenets

Built for people who ship with agents and still want the wheel.

The card is the source of truth

Every plan, review, and test result is signed back onto the card. A resumed session — or a teammate — can reconstruct exactly what happened.

Human-gated by default

It pauses at plan and code review. Full autonomy is opt-in, per run. You decide how long the leash is.

Provider-agnostic

Agent roles are defined by function, not vendor. A routing table maps each role to whatever LLM you choose.

Self-host first

One docker compose up. Your data, your keys, your machine. Credentials encrypted at rest, never returned in plaintext.

Correctness over speed

The pipeline refines before it builds and reviews before it ships. A circuit breaker stops a card that can't satisfy its gates.

A real board, not a chat log

Columns, cards, drag-to-move, a live run feed. Supervising many parallel agent runs should feel like mission control.

Who it's for

Solo builders first. Teams next.

If you already run coding agents and want a durable, reviewable process around them — this is for you.

Solo developers Indie hackers AI-native builders Small dev teams & agencies Anyone tired of moving cards by hand
Questions

What Daikonbun is — and isn't.

What is Daikonbun?
A self-hostable task board that runs itself. You drop a rough task onto a kanban board and a pipeline of specialized AI agents refines, plans, reviews, builds, and verifies it — pausing for you only at the review gates that matter. Every agent signs its work onto the card, so the card becomes a complete, auditable record of how the work was done.
How is it different from Trello, Jira, or Linear?
Those boards track work but don't do it. AI coding agents do work but have no durable, multi-stage, reviewable process around them. Daikonbun is the process layer for AI-assisted work: opinionated stages, explicit review gates, a durable signed record on every card, and a human in the loop by default.
Is it really self-hosted?
Yes — one docker compose up runs the board and its database on your own machine. Your data, your API keys, your infrastructure. A hosted option may come later, but self-host is the primary product.
Which AI models does it use?
It's provider-agnostic. Each agent role maps to a model through a routing table you control — so you bring your own LLM and route stronger models to planning and review, cheaper ones to mechanical steps.
Is my data private?
Because Daikonbun is self-hosted, your tasks, credentials, and work records stay on your machine. Credentials are encrypted at rest and never returned in plaintext by any API.
When does it launch, and is it free?
It's in active development. Join the launch list to be notified when it goes live. It will be free for noncommercial self-host, with a commercial license for paid use.
Launching soon

Be first through the gate.

One email when Daikonbun ships. Early self-host access, the docs, and the day-one release.