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.
See AITaskManager in Action
Click any tab to explore. Click the image to zoom.
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.
Create a Task
One prompt with title, project, and priority. That's the only manual step.
Branch & Isolate
AITM creates a dedicated git worktree and branch. Your main branch is never touched until the change is proven.
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.
Review → Auto-Fix
A review agent checks quality and security. Any finding automatically triggers a fix agent — no round trip back to you.
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.
Docs Auto-Update
Behavioral contracts and documentation are regenerated from the merged change — docs never go stale.
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.
AITM vs. Plain AI Coding Tools
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.
| Dimension | Claude Code / Cursor | AITM |
|---|---|---|
| Workflow | Chat → paste code yourself | Task → full pipeline → auto-merged PR |
| Project knowledge | None — starts blank every session | Behavioral contracts + code map + DOM map, read before coding |
| Context | Lost between messages | One shared session across design → code → review → fix |
| Risk | Changes land directly on your branch | Isolated git worktree; main branch always safe |
| Review | Manual, if you remember to ask | Automatic — review agent runs every time |
| Tests | You write and run them yourself | Unit + E2E tests run automatically, hands-off |
| Docs | Go stale the moment code changes | Auto-updated after every merge |
| Multi-project | Separate chat per project, no shared queue | One dashboard, shared priority queue across all projects |
| Model choice | Locked to one model per session | Mix providers per pipeline step — Claude for code, Gemini for review, etc. |
| Recovery | You notice it stalled, you restart it | Watchdog detects and retries automatically |
Why AITaskManager?
Everything you'd have to do by hand with a plain AI coding tool — automated.
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 — mix providers per 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.
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.
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.
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.
User Guide
Learn how to use every feature. Click to expand.
Creating a Task
Write a title and prompt describing what you need. Select the solution (project group) and specific project. Set priority, choose which pipeline steps to run, and optionally add dependencies on other tasks. Click "Create" and the task enters the queue.
Read the full guide →
Monitoring the Pipeline
The Dev Dashboard shows active pipelines with colored step indicators: passed running pending. Live console streams AI output. Click any step to see its details. Stop, resume, or skip steps anytime.
Read the full guide →
Viewing Results
After pipeline completes, click "Result" to see the full summary: branch name, commit link, files changed, step durations, cost breakdown. The result includes the original prompt, architecture plan, and links to the actual code diff.
Read the full guide →
Testing & Verdicts
The Testing view shows test history with pass/fail charts over time. Run unit tests per project, view E2E test plans with scenarios, and record manual verdicts. Each test run captures screenshots for visual regression checking.
Read the full guide →
Contracts & GraphQL
Every feature is documented as a behavioral contract with test coverage status. The interactive graph shows module relationships. Query contracts via GraphQL to find which files implement specific behaviors. AI reads these before coding.
Read the full guide →
DOM Explorer & Code Graph
Visualize your entire codebase as an interactive dependency graph. Files are clustered into communities by import patterns. Identify "god nodes" (high-dependency files), find unused code, and understand module boundaries at a glance.
Read the full guide →
Archive & History
All completed tasks are auto-archived with full metadata: branch, commit, step timings, cost, and result summary. Filter by project, search by title or task number. Restore any archived task to re-run or modify it.
Read the full guide →
Settings & Configuration
Configure AI models per step, pipeline behavior, git settings, watchdog thresholds, editor autocomplete triggers, keyboard shortcuts, and system resources. Add new projects with the Project Wizard — one-click onboarding.
Read the full guide →AI Chat & Brainstorm
Open the floating Chat panel to ask questions about your project — AI has full context via contracts, code maps, and hints. Use Brainstorm panel to explore ideas, then convert the best ones into tasks with one click.
Read the full guide →