A plan in a markdown file
Your team sees it. Your agent does not.
It sits in the repo, reviewed and current — and every session still starts with you pasting it into the prompt again.
The roadmapyour coding agentscan actually read.
Plan your work on a board the whole team can see. Your coding agent picks up a card, does the work on your own machine, and posts back what it did. Then it waits for someone to read it and say it is done.
cawdev is not open to everyone yet. We are letting in a few teams at a time so we can fix things properly with each one.
cawdev · roadmap · cawdev/console
- 1plan, read by people and agents
- 0context to paste each session
- 3commands to set up a machine
Why cawdev
You wrote the plan down. Your agent still cannot see it.
Every team building with agents keeps the plan somewhere. Both of the usual places cost you something.
A plan in a tracker
A nice board your agent cannot use.
People can read it, so the plan is at least somewhere real. Your agent gets an API and a login that were never meant for it.
Either way
No record of the work.
Nothing tracks which session touched what, what it asked you, or what it changed. It all disappears when the terminal closes.
cawdev keeps one plan that your team and your agents both read.
How it works
From idea to shipped, without repeating yourself.
Four steps. The card is the unit of work in every one of them.
- 01
Write the card
Add what you want built to the board — or file what is broken, with a severity. Type it yourself, or describe it in a sentence and let an agent draft it for you to edit.
Considering → Planned → In development → Merged → Shipped
- 02
Hand it to your agent
Connect your agent to the board once per repo. From then on it can read the board, pick up a card, comment on it and move it along.
One entry in .mcp.json — nothing to install
- 03
Press start
The work runs on your own machine, in its own copy of the repo. Start several cards at once and say up front whether they share a branch in order or take one each in parallel.
A fresh workspace for every run
- 04
Answer, then say it is done
When the session needs a decision it asks you and waits, instead of guessing. When it finishes, the branch waits to be read — done, or not done with a note the next session is handed.
Allow once · for this session · for the project
What you get
The same board, for different reasons.
Pick the one that sounds like you.
Stop re-explaining the plan every session.
You already wrote down what to build. Your agent should just read it.
- The card is the prompt
- Your agent pulls the card, its status and the thinking behind it. Nothing to paste, and nothing that went stale last week.
- It runs on your machine
- Sessions work in your own checkout with your own credentials. cawdev never clones your repo and never holds a git login.
- It asks before it acts
- Hit something it has no permission for and it stops and asks. Allow it once, for the rest of the session, or for the project.
- Or stay in your terminal
- One command shows every session on the machine and lets you answer one. The transcript goes into your own scrollback, so it is still there tomorrow.
Five repos, or fifty. One place to look.
A board per project, and no ceremony piled on top of it.
- Every project in one place
- Each project points at a repo and has its own board and its own people. One install covers all of them.
- One page for what is waiting
- Planned, broken and in flight, per project and across all of them, with the projects that need you first. Every number opens the board it came from.
- Release notes you did not write
- The changelog is built from what actually shipped, grouped by release and in the right order. No more writing it the night before.
- Several cards at once
- Every run gets its own copy of the repo, so parallel sessions never fight over the same checkout. A run that fails is carried on or started over, not lost.
Agent work you can account for.
Who asked for what, who approved it, and what changed — all written down.
- It stays on your infrastructure
- The board, the database and the sessions all run inside your own network, next to the code they work on.
- Work lands the way you say
- A project decides whether a run opens a pull request and whether anything reaches the main branch unread. A session that needs a review waits for one.
- Nothing is quietly deleted
- Cards and comments are never removed. Turning an idea down takes a written reason — which is what stops it coming back next quarter.
- Every run has an owner
- The person who started it answers its questions, and their name stays on the card alongside what the session did. An agent reaches only what its owner can reach right now.
In the console
Built for the part where the agent is working.
Not a dashboard you check afterwards. It is where the work happens.
Watch the session live
Every run, streaming as it goes. Read what the agent is doing, type to it mid-run, or stop it — from the console, or from your own terminal.
Questions reach a person
The agent’s question goes to whoever started the run. Answer a dozen at once as one form, or pass one on.
Permissions that fit
Allow a tool once, for the rest of the session, or for the whole project. Not one big switch.
A board of branches
Cards say what to build. Beside them, the branches: being worked, waiting to be read, signed off, or sent back with a note.
Docs that stay true
ROADMAP.md, CHANGELOG.md and ISSUES.md are generated from the board, and cawdev tells you when the files have drifted.
Straight answers
The questions you were going to ask anyway.
Only if you are in the beta. We are running with a small number of teams on purpose — few enough that we can sit with each one, watch where it breaks, and fix it before the next team arrives. Ask for a spot and we will tell you where the queue stands.
By fit, not by order. We take teams already running coding agents daily with a real backlog to point them at, and we keep the group small enough to support properly. Tell us what you are building and you will hear back either way.
Nothing during the beta. There is no card to enter and no trial clock. We will never resell your model usage either — you bring your own Claude subscription, and those tokens stay billed to you.
No. You keep your repo, your editor and your agent — and your tracker, if you have one. cawdev is where agent work is directed and recorded, not where the company plans its quarter.
On your own machines. The board and its database sit on your infrastructure, and runs happen in a copy of your own checkout with your own git credentials, so cawdev never needs a git login. There is no hosted version yet.
Claude Code. You choose the model and how hard it thinks for each run, with a default per person. A second agent is on the roadmap and not built.
Anything outside what you have allowed stops and asks you first. Each machine also carries its own ceiling of what may ever run unattended, and no project rule can widen it.
It stays yours. Your data lives in your own database, and the roadmap and changelog are ordinary markdown files in your repo. Nothing is locked in a format only we can read.
Limited beta
Ask for a spot in the beta.
cawdev is open to a small number of teams at a time. Tell us what you are building and who is building it, and we will get back to you when the next spot opens.