<> AutoAIDev
Products
One belief · three doors

Same engine, wherever you'd rather watch it run

These aren't three products — they're three windows onto one loop and one TODO.md. Use the extension while you're coding, the CLI when you want it running headless overnight, the dashboard when several repos are going at once. Switch mid-backlog; the repo won't notice.

VS Code / Cursor Extension
Windows · macOS · Linux

Automation you never have to switch to

The best tool is the one you forget you installed. A panel drives the loop against the workspace already open in front of you; tasks move from [ ] to [~] to [x] in the file itself, and every change arrives in the diff view you already trust. Nothing new to learn, nothing new to watch.

  • Start, pause and stop the loop from the panel
  • Pick the provider per workspace
  • Live log of dispatches and completions
Open in Marketplace Source
AUTOAIDEV · PANEL
provider  claude-tui
workspace ~/apps/storefront
status    running
queue     3 pending · 1 active
autodev-cli
Any OS · Terminal

The part you can leave running overnight

The engine itself, headless — no window, no attention required. Live over SSH, inside tmux, or on a spare box that keeps working while you sleep. Resume, hard timeouts and rate-limit backoff are not add-ons here; they are the reason walking away is safe.

  • autodev start . — drain the TODO in this repo
  • --provider grok|copilot|opencode
  • --timeout 30m, --no-resume
View on npm
$ npm i -g autodev-cli
$ cd ~/apps/storefront
$ autodev start . --provider claude
[AutoDev] loop running — 4 tasks queued
Desktop App
Linux x86_64

One glance, every project moving

When the loop is solved, the interesting question stops being is it done? and becomes what else could be running? The dashboard answers it: every repo in a row, live status, queue depth, log tail. No terminal required.

  • Add a folder, pick a provider, hit run
  • Per-project pause, stop and log view
  • Ships as a ready-to-run download
Get the desktop app
PROJECTQUEUESTATE
storefront3running
billing-api7running
docs-site0idle
infra-scripts2paused
What sets us apart
Differentiators

What sets AutoDev apart

Three things most AI-agent tools can't do — connect in one step, agents that actually remember, and identity that survives a model switch.

01 · SETUP
Zero setup friction

Connect and go — no config marathon.

Spin up an office and put agents to work with a single command or connect flow. No lengthy setup or wiring before you see value.

Others make you configure before you can start. We let you start, then configure.

02 · MEMORY
Permanent memory

Your agents remember.

A persistent knowledge-graph memory plus a durable, cross-session, cross-agent project graph mean an agent carries what it learned into every future session and task. Nothing has to be re-explained.

Others reset to zero every session. Ours pick up where they left off.

03 · IDENTITY
Provider-portable identity

Switch the model, keep the agent.

Move an agent between Claude, grok, opencode, or Copilot at any time and its name, memory, history, and tasks all stay intact. The provider is a setting, not a cage.

Others lock you to one model — or lose the agent when you switch. We keep the agent; you swap the engine.