<> AutoAIDev
How it works
How we solved it

The hard part isn't writing code. It's knowing when to move on.

An agent that says "done" when it isn't will quietly wreck a five-task run — which is why people hover, and why nothing is truly automated. So the loop below is deliberately boring: a plain checkbox file as the only source of truth, completion judged on the exact line the agent claimed, and a defined way out of every stall. Boring is what lets you close the laptop. Identical behaviour in the extension, the CLI and the desktop app.

1
Keep a TODO.md with a ## Todo section of - [ ] checkboxes.
2
Start the loop. AutoAIDev picks the first unchecked task and marks it [~] in progress.
3
The task text is dispatched to your provider CLI — Claude, Grok, Copilot or OpenCode.
4
It watches that exact line — by number, not by text — until the agent writes [x] with a date.
5
Next task. When the list empties it polls — add a line and work resumes on its own.
Task status model
[ ]
Pending
Waiting in the queue.
[~]
In progress
Dispatched; the loop is watching that line.
[x]
Done
Agent checked it off with a completion date.
[!]
Timed out / rate-limited
Reset to [ ]; the loop pauses until the parsed reset time, then retries.
providers: claude · grok · copilot · opencode
default timeout: 30 min per task
resume: on by default
TODO.md
## Todo
- [x] 2026-08-01 build login page
- [~] refactor auth module
- [ ] add password reset flow
- [ ] write integration tests

One file — the only source of truth the loop reads and writes.

[ ] pending [~] in progress [x] done [!] retried
Robustness

Completion it cannot fake. Done is keyed to the exact line the loop claimed — not to matching text — so a reworded or reshuffled list never tricks it into moving on early.

A way out of every stall. Anything still thinking after 30 minutes is retried or set aside. One bad task never holds the whole list hostage.

Patience, handled for you. Hit a rate limit and the task returns to [ ] while the loop sleeps until the quota resets — then carries on exactly where it stopped. You find out afterwards, not at 2am.

The problem of agent soul
The deeper problem

The loop keeps working. The agent should keep being itself.

“Most people are other people. Their thoughts are someone else’s opinions, their lives a mimicry, their passions a quotation.”
— Oscar Wilde, De Profundis

A raw large language model is exactly the mimic Wilde describes. It has no self of its own: no memory of yesterday, no fixed identity, no judgment accumulated across the work. Each session it becomes whoever the prompt makes it, and its "passions" are a quotation of the system message. Point the same model at the same repo twice and two strangers show up. An agent is meant to be your proxy — but a proxy with no soul is just a stranger wearing your name badge.

The task loop above solves continuity of work — the list keeps draining. Underneath it, AutoDev gives each agent continuity of self, so the thing draining the list is the same colleague from one session to the next. Three parts make up that soul.

01 · IDENTITY
A durable identity & profile

Each agent keeps a persistent identity and profile — a name, a role, and a self-description it builds by proactively discovering what it is and verifying that against its own work, rather than being re-invented by every fresh prompt. The identity travels with the agent even when you switch the underlying model.

02 · MEMORY
A cross-session memory graph

Decisions, conventions and how the pieces of a codebase connect are written into a durable knowledge and project graph the agent reads back on later tasks. What it learned on task three is still there on task fifty — and still there tomorrow — instead of being re-discovered from cold each run.

03 · CONTINUITY
Continuity across sessions

Sessions resume by default, so an interrupted run picks up its own thread rather than starting over as a stranger. History, tasks and memory stay attached to the agent, and the provider becomes a setting you can change — not an identity the agent loses when it does.

Nothing here invents new intelligence — it is the same model you already pay for. The soul is simply everything the agent is allowed to keep between the moments it is thinking.

Next: the loop is the same everywhere — choose where you want to watch it happen.
Products →