⚠️ Release 08/2026 — AITM is still in active development and testing.

AITM is used by development teams and solo developers who want to hand off routine coding to AI agents while staying focused on architecture and decisions. It solves the chaos of parallel tasks, lost context between conversations, and the need to manually review every code change. They need a tool that guarantees worktree isolation, automated testing, and an auditable history — without sacrificing development speed. AITM gives them confidence that AI-generated code goes through the same discipline as human-written code, while saving hours every day.

From Prompt to Merged PR — Fully Automated

Submit a Task.
Ship Tested, Merged Code.

Describe what you need once. AITM designs the approach, writes the code, reviews it, fixes what's broken, tests it end-to-end, updates the docs, and merges it to your main branch — without you touching a keyboard again until it's done.

🕒 Release coming soon
08/2026
See It in Action

See AITaskManager in Action

Click any tab to explore. Click the image to zoom.

Dev Dashboard Create Task Task Result Testing Dashboard Contracts Graph DOM Explorer Archive Settings
Dev Dashboard — Your Command Center

See all your projects, active pipelines, git status, and task queue at a glance. Live console streaming shows AI working in real time. Drag and drop tasks to reorder priority.

How It Works

A real 9-step pipeline — architect, code, review, fix, test, e2e, docs, merge — told step by step.

1
Create a Task

One prompt with title, project, and priority. That's the only manual step.

2
Branch & Isolate

AITM creates a dedicated git worktree and branch. Your main branch is never touched until the change is proven.

3
Design & Code — One Conversation

The architect plans the change and the coder implements it in the same AI session, so nothing gets lost between planning and building.

4
Review → Auto-Fix

A review agent checks quality and security. Any finding automatically triggers a fix agent — no round trip back to you.

5
Test + E2E, in Parallel

Unit tests and Playwright end-to-end scenarios run together in an isolated app instance, so testing never blocks on itself.

6
Docs Auto-Update

Behavioral contracts and documentation are regenerated from the merged change — docs never go stale.

7
Auto-Merge, Watched

AI resolves merge conflicts and merges to your main branch. A watchdog detects and retries any step that fails — hands-off from start to finish.

Why AITaskManager?

Everything you'd have to do by hand with a plain AI coding tool — automated.

Pipeline & Automation
Never Touch a Terminal Again

Branch, architect, code, review, fix, test, e2e, docs, merge — one pipeline runs every step for you. Skip any step or resume from failure.

🤖
Use the Best AI for Each Job

Claude for code, Gemini for review, DeepSeek for tests, a local Ollama model for mechanical steps — pick both the provider and the model independently for every pipeline step, and cut cost without cutting quality.

📜
Stop Getting Hallucinated APIs

Every feature is a testable behavioral contract. AI reads it before coding, so it stops guessing file paths and inventing methods that don't exist.

🌿
Your Main Branch Is Always Safe

Every task runs in its own worktree and branch. Nothing touches dev until it's tested and reviewed.

🧪
Ship Without Manually Testing

Unit tests and Playwright E2E run automatically on every task, with visual regression screenshots so UI breakage can't sneak through.

🔍
See Exactly What Your Codebase Looks Like

An interactive dependency graph shows file communities, god nodes, and import relationships — no more guessing what a file touches.

Intelligence & Observability
💬
Turn a Conversation Into a Task in One Click

Chat with full project context, brainstorm the approach, then send it straight to the queue.

🛡
It Recovers So You Don't Have To

A background watchdog catches stuck tasks and zombie processes and restarts failed steps automatically.

📊
Your AI Learns Your Codebase's Patterns

Reusable hints inject project-specific conventions into every prompt — type ~hint for instant context.

📁
Run Every Project From One Screen

Switch context instantly, queue tasks across projects, and track progress everywhere at once.

📺
Watch the AI Work in Real Time

Full transparency into every command, file change, and decision as it happens.

Queue Tonight, Wake Up to Merged Features

Queue 20 tasks before bed with priorities and dependencies — AITM runs them sequentially while you sleep.

Works with any AI model
⚡ Claude ⬣ Gemini 💡 DeepSeek 🦙 Ollama + Any LLM via API

All of these are fully usable across AITM — not just for coding. Chat, Brainstorm, and every pipeline step (architect, code, review, fix, test, e2e, docs) can each use a different provider and model, with independent settings for each provider.

AITM Learns Your Project

The more AITM works on your codebase, the less it has to re-discover every time.

📜

Behavioral contracts capture what your code does — checked before every edit, kept in sync after every merge.

🕸

A knowledge graph links variables, contracts, DOM elements, tests, and docs behind one query.

🗺

Import a repo and AITM maps its stack, code, and UI before the first task ever runs.

🔁

Shared agent templates and structured handoffs keep every AI session — and every provider — on the same page.

Measurable Efficiency Gains

Compared to manually prompting AI in a chat window.

70-85%
Less Hallucination
Behavioral contracts and code maps ground AI in actual codebase reality. No guessing file paths or APIs. That's why hallucinated code drops 70-85%: the AI reads verified specs instead of inventing them.
contracts + code_map + hints
5-10x
Faster Delivery
Queue 20 tasks before bed. Wake up to 20 merged features. Zero supervision needed overnight — that's why delivery speeds up 5-10x: the pipeline runs continuously instead of waiting on you between steps.
parallel pipeline + auto-queue
90%+
First-Pass Success
Architect + Review + Fix cycle catches issues before you see the result. That's why 90%+ of tasks merge without manual intervention: mistakes get caught and corrected inside the pipeline, not after.
architect → review → fix loop
40-60%
Token Savings
Hints, keywords, and contracts inject context without repeating it. AI reads only what it needs — that's why tokens drop 40-60%: no more re-explaining the codebase in every prompt.
vs. copy-pasting context manually

Stop Babysitting Your AI. Start Shipping.

Every night you skip is a night of merged features you didn't ship. Queue your backlog now — AITM starts orchestrating the moment it launches.

🕒 Release coming soon
08/2026

How licensing works →

User Guide

Learn how to use every feature. Click to expand.

36102
Unit Tests Passing
2450 test files
226367
Lines of Production Code
997 TS files
2370
Behavioral Contracts
298 modules
440
Tasks Completed by AI
auto-archived
3791
Documentation Pages
auto-generated

One System — GUI, Pipeline, Data, and Contracts

AITM doesn't replace Claude Code, Cursor, or your favorite AI coding tool — it orchestrates them. Point it at the same models you already use; it adds the pipeline, safety net, and project memory around them.

🖥️
Visual layer you can actually see

A live dashboard shows every project, running pipeline, and queued task in real time. The DOM Explorer maps each UI element to its data-aitm code, and screenshot history keeps a visual record of how each screen changed over time.

⚙️
A pipeline, not a chat window

One prompt runs the full 9-step pipeline — architect → code → review → fix → test → docs → merge. Each task gets its own isolated git worktree, so your main branch is never touched mid-run, and a watchdog detects stalled steps and retries them automatically.

🗄️
Everything is stored, nothing is guessed

Each project has its own database holding behavioral contracts and task history. A global database holds settings, hints, and the variable registry shared across projects. Every task keeps its own log folder and archived result, so you can go back to any run later.

🔒
Strict data separation between projects

One project's data never mixes with another's — each project keeps its own separate database file. Work in progress stays inside its own worktree until it is reviewed, tested, and merged, so nothing half-finished leaks into the main branch.

🔗
Data, business logic, and GUI are linked

Every UI element carries a data-aitm code tied to a behavioral contract that describes its expected behavior and points at the exact source file and variable in code. AI agents read that verified specification instead of guessing intent from raw source.