Skip to content

Get visibility into your team’s development pipeline

Give executives and stakeholders a shared view of what your team has planned, what is in progress, and what has been delivered.

From plans and expectations to a high-quality spec and working code

The most natural, direct way from intent to implementation. Shape the spec in chat, approve the plan, and let agents build.

A control plane for Claude Code, Codex, and Pi

Swap agents per task and run them in parallel. Project rules go in; the record of what the agent did comes back on the task.

94% of Tipatask has been built using Tipatask

Planned in its own chat, tracked on its own board, implemented by its own agent sessions.

Join Beta See how it works

The problem

Agents made writing code fast. Deciding what to build stayed manual.

Context gets lost between chat sessions, terminal history, and task notes that live nowhere in particular. The bottleneck today isn’t code generation — it’s context control.

How it works

From plans and expectations to a spec, then working code.

Spec-Driven Development turns team input into a clear specification, an approved plan, and code you can review.

Executives, stakeholders, and developers share their plans, expectations, and desired outcomes.

Sprint 121 remaining Progress bar67%
TPT66Completed

Scaffold standalone Laravel site

tt-website-laravel
TPT52Completed

Website style guide and insignia palette

css
TPT68In Progress

Landing page L1–L15 sections

landing-page
+ Add item
Web app — sprint board.

Describe them in your own words. The planning chat uses the project’s tasks and architecture to shape a clear, complete spec.

Build the public landing page: fifteen sections from the page map, in English and Ukrainian, styled with the site style guide. Every section must render in both locales.

ModelOpus 5 Embed Import... Send
Task App — planning chat, new objective.

Review the spec and proposed tasks. You approve what will be built before an agent starts.

Proposed tasks:

NEW
newScaffold standalone Laravel site

1. @website/routes/web.php — serve the landing page at the root and the Ukrainian path from one localized route. 2. @website/public/css/marketing.css — copy the token block from the style guide.

NEW
newLanding page L1–L15 sections

1. @website/resources/views/landing.blade.php — build the fifteen page-map sections on their assigned grounds. Verify every section id renders in both locales. 2. @website/lang/en/landing.php — one key per visible string.

PendingSprint 12 Deps: TPT66
tt-website-laravellanding-pagecss
Accept proposal Reject proposal

Files Addressed (3)

Agent edits during analysis (1)

2 tasks ready to saveDiscardSave Tasks
Task App — planning chat, proposed tasks.

Each task carries its approved specification, dependencies, and the project knowledge it needs.

Sprint 123
TPT68Landing page L1–L15 sections Highlight related cards Rehash the description Delete this card Select this card
Pending Start

Deps: TPT66

1. @website/resources/views/landing.blade.php — build the fifteen page-map sections on their assigned grounds. Verify every section id renders in both locales. 2. @website/lang/en/landing.php — one key per visible string.

csslanding-pagett-website-laravel
Assigned to Anton Agent badge
TPT69Ukrainian locale for the landing page

1. @website/lang/uk/landing.php — translate every key; identical values only for the untranslated-by-design set.

TPT71Testimonials band

1. @website/resources/views/landing.blade.php — add a band between the personas and the roadmap with six speech-bubble tiles.

Task App — task board.

Launch an agent from the task to turn the approved spec into working code, on your machine, in your checkout.

TPT68 - Landing page L1–L15 sections · Claude Code · Opus 5 Show TaskTerminateMinimize

[Task App] Auto-approved project MCP servers.

[Task App] Planning mode. Review the plan, then type /approve-plan and press Enter to continue.

/approve-plan

[Task App] Plan approved. Continuing in execution mode.

--- Process exited (code 0) ---

Tokens: 48,210 in / 9,377 out
Task App — agent console.

Review working code against the spec. The task keeps the result and updated project knowledge, so stakeholders can follow delivery.

tipatask · MCP server · stdio

pull_knowledge()

{ "pulledCount": 2 }

get_tag_architectures({ "tag_names": ["tt-website-laravel"] })

ai/architecture/tt-website-laravel.md

push_knowledge({ "file_key": "ai/architecture/GENERAL.md" })

{ "pushed": 1 }

KB synced — 1 pushed, 2 pulled

Agent session — knowledge sync.

Task management and communication

Your development pipeline, visible to everyone who needs it.

Give executives, stakeholders, and developers one shared view of plans, progress, and results. Plan, assign, and discuss work on the same task record.

  • Board, backlog, sprints, kanban, and epics.
  • Custom statuses, subtasks, and objectives.
  • Comments, mentions, and notifications.
  • Owner, editor, and viewer roles.
  • Desktop app for macOS, Windows, and Linux, plus a web app.
  • Issue, card, and email import.
tipatask
176 tasks
apppixies-site
31 tasks
internal-tools
12 tasks
CompletedIn ProgressPending
Web app — dashboard, projects.

Project memory

Your project remembers itself between agent sessions.

Architecture knowledge lives with the project, so every agent starts informed and leaves the project better documented.

  • Architecture docs kept in your repository and in sync.
  • Agents read them before a task and update them after.
  • Every task keeps its specification, resolution, and token counts.
  • Available to any agent through MCP.

Swappable parallel agents

Pick the agent per task. Run several at once.

Spec-Driven Development turns your approved spec into working code. Each agent works from the same clear scope and project knowledge.

  • Claude Code, Codex, and Pi run tasks.
  • Works with virtually any publicly available model.
  • Switch agent or model on any task.
  • Parallel sessions across tasks and devices.
  • Plan approval before any code is written.
  • Git and Subversion integration.

What makes us different

Built around agent-executed work, not retrofitted for it.

Both contrasts reduce to one discipline: Spec-Driven Development. A human approves the specification before execution, and the result is reviewed against it.

Against generic AI app builders

Prompt-to-app tools optimize for something that runs quickly, with no durable plan behind it. Tipatask governs ongoing work, task by task, with a record attached to each one.

Against cloud task boards and AI workspaces

Most task tools were built for humans coordinating with humans, with AI added as a chat feature. Tipatask starts from a task record an agent can read and act on directly.

Who it’s for

For developers already running agents every day.

Solo developers

Tipatask remembers the project across sessions — the plan, what got tried, the architecture — without a workflow heavier than the work itself.

Engineering leads

Task specs an agent can execute, and agent work that is reviewable the same way human work already is.

AI-native founders

One surface for objectives, architecture context, and execution.

News

Latest updates

All news and release notes

Version 0.9.19 Changelog

Tipatask 0.9.19

Tipatask 0.9.19 makes whole projects portable. A new export option packs a project's knowledge base and all open tasks, with their sprints, tags and statuses, into a single zip archive. Importing it creates a fresh project through a short wizard that asks for a name, folder and agents. Files…

Version 0.9.17 Changelog

Tipatask 0.9.17

Agent permission modes. Image-generation tasks with OpenRouter. Objectives keep their source material.

Roadmap

What is built, what is being built, and what is planned.

Every shipped feature, with the tasks that built it, is on the roadmap page.

See the full roadmap

94% of Tipatask has been built using Tipatask

94% built with Tipatask 6% by hand

Tasks tracked
2,282
Tasks completed
2,196
Sprints
318
Knowledge base documents
113
Saved planning prompts
1,022

Tasks by Agent

  • Claude Code 1,328
  • Codex 312
  • Pi 5
  • People 53

Task management, architecture memory, and agent execution — in one place, next to your repo. Tipatask is bridging the gap between planning and execution.

Join Beta

Testimonials

What people say

Nothing of that would be required, you know.
— Odysseus
Easy peasy!
— Sisyphus
Team work is the key.
— Hercules
Delegation is all about trust.
— Julius Caesar
No more tasks hanging.
— Damocles
I love the big-picture view.
— Icarus