Run your backlog through
agent workflows — on your machines.
Design the steps with an agent, hand it a work item, and let advancement rules decide when work advances. Every step runs on your own machines and leaves artifacts — traces, logs, outputs — you can inspect.
What do you want the agent to do?
Workflows are yours to define — the steps, the models, and the advancement rules that gate each one. These are the shapes teams usually start with.
Fix bugs from tickets
Ingest a bug from GitHub or Jira. The agent reproduces it in a live browser, the step passes evaluation, and the fix step starts with the repro as context.
Ship backlog features
Write a work item in the dashboard with enough detail to act on. The agent implements it step by step, and advancement rules gate what counts as done.
Raise test coverage
Point a workflow at under-tested code. The agent writes failing-first tests, and the workflow only advances when the suite actually runs and passes.
Triage and hand off
Let the agent reproduce and document incoming issues — traces, logs, and screenshots attached as artifacts — then hand a confirmed repro to a human.
The workflow layer between your backlog and your machines.
Boboddy coordinates the workflow — steps, evaluation, artifacts — while the execution stays on infrastructure you control.
Work items from anywhere
Create work items in the dashboard, or ingest them from GitHub and Jira. Either way, the agent starts from a description your team actually wrote.
Signals decide advancement
Each step reports structured signals, and your advancement rules decide what happens next — advance, loop back, or block for a human. No vibes-based “done”.
Artifacts on every step
Traces, logs, screenshots, and outputs are saved to the step that produced them. Open the Playwright trace the agent captured, right from the execution page.
Your devcontainer, your machines
Workers run on hardware you control. Steps that need your code run inside your project's own devcontainer — the same environment your team develops in.
Bring your own AI
Use the model that fits each step. API keys stay with your workers, so the control plane coordinates the workflow without owning your credentials.
Context in, questions out
The agent reads your business context — personas, product flows, terminology — before every run, and asks for feedback through notifications when it's blocked.
From work item to evaluated result.
Link a repo, design the pipeline with an agent, give it work. Workers run every step on your machines, and nothing advances until its advancement rules say so.
Link your repo
Install the CLI and run init in your repo. It signs you in and links the repo to a project. No devcontainer yet? The designer writes one when a step needs your code.
$ npm i -g @boboddy/cli
$ boboddy init
◇ Signed in as you@example.com [14s]
◇ Created project “my-repo” [4s]
◇ No devcontainer yet [0s]
◆ Design your first pipeline now?
│ ● Yes / ○ NoDesign it with an agent
Pick a work item. The designer interviews you about it and writes the pipeline; the studio draws it as it goes.
Say this one landed overnight and an agent picked it up — what would you want waiting for you in the morning?
Give it work
Create a work item in the dashboard with enough detail for the agent to act on it — or ingest one straight from GitHub or Jira.
Run workers, inspect artifacts
Workers on your machines claim each step and run the agent, inside your devcontainer when the step needs your code. Logs stream to the dashboard, and every step leaves artifacts you can open, including full Playwright traces.
$ boboddy work
┌ Boboddy worker
◆ Worker ready (<worker-id>)
● Claimed 1 step
◇ step <step-id> starting devcontainer… [0s]
◇ Step <step-id> succeeded (2m 26s) [2m 16s]
● Claimed 1 stepSelf-hosted by default. No compromise.
Boboddy ships the control plane. You bring the workers. The result is a platform with the polish of a SaaS and the trust boundary of on-prem.
Your code never leaves your network
Workers clone, run, and report from inside your perimeter. Source, build artifacts, and intermediate state stay on your hardware.
Your AI provider, your API keys
Credentials live on the worker, not the control plane. Swap providers per project or per step without giving up keys to anyone.
Runs in your own devcontainer
Steps that touch your code run inside your project's devcontainer on your worker — the environment you already trust, with the boundaries you already set.
Pay for compute you already own
Shared execution planes charge for cycles you don't need. Boboddy runs on the machines you have, at the cost you already pay.
Put your backlog on agent workflows you can actually trust.
Design the steps once, then let evaluated agents work through the queue — on machines you already control, leaving artifacts at every step.