One-page explainer
Manage AI coding work from one place.
AI coding assistants are powerful but chaotic - you chat with one in one window, lose track of what it did, and start over tomorrow. aidd turns them into a managed workforce: it hands out the work, checks the results, and keeps the records.
Pick your background
This page is the general tour. If you're coming from a specific kind of tool, there's a version written for you:
The problem it solves
Using an AI assistant to build software today feels like supervising a brilliant intern with no memory. Every session starts from scratch. Nothing forces the AI to plan before it types, nobody reviews its work, and if you have several projects, you're juggling several separate conversations with no overview of any of them.
aidd adds the missing management layer. It's a small app that runs entirely on your own computer and gives you one local control panel where you launch AI work, watch it happen, and review what came out - across every project you own. In current market language, it is a local, agent-agnostic agentic development environment: delegated work and durable results are the primary units, not files in an editor.
How it works
Instead of one long freeform chat, aidd pushes every piece of work through a disciplined loop - the same one a good engineering team uses:
Plan
The AI writes down what it intends to do before touching anything.
Build
It does the work in small, tracked steps you can watch live.
Verify
Work only counts as done after tests and automated checks actually pass.
Record
Every run keeps its receipts - what changed, what it cost, and why.
Every run is recorded, so you can always answer "what changed, and why?"
What's inside
One dashboard, all your projects
Projects, running jobs, results, and history live in a single local web page - no more tab archaeology.
A director for the whole fleet
A built-in "Director" looks across everything you're building and suggests what's worth doing next. You can chat with it, and it can kick off work for you.
Repeatable playbooks
Save multi-step workflows as recipes - "review, fix, verify" - and rerun them on any project with one click, or put them on a schedule and let them run unattended, instead of re-explaining every time.
Built-in quality inspections
Ready-made audits scan for security holes, performance issues, and messy architecture, and file what they find as tasks.
Bring your own AI
It works with the assistants and models you already use - ten backends in all, including Claude Code, Codex, Cline and opencode, OpenAI-compatible services, and models running privately on your own machine through Ollama or LM Studio.
Steer it from your phone
A Telegram bridge, included with aidd, lets you message the Director from anywhere and have it start supervised work while you're away from the desk - once you connect your own bot and allow-list your chat.
Private by design. aidd has no account and no hosted control plane; it sends no telemetry and does not phone home. Your projects, run history, and settings stay on your computer - the usage dashboard inside the panel reads a local database and nothing else - and network traffic comes only from the AI providers or integrations you configure, or downloads you initiate.
Who it's for
Anyone using AI to build or maintain software who wants more than a chat window: solo developers running several projects, tinkerers who want their AI work to be repeatable and reviewable, and people on teams experimenting with agent-driven development who need visibility into what the machines actually did. aidd is a single-operator tool - there are no accounts or shared workspaces, so each person runs their own local panel.