Weft alternative

Done vs Weft

The closest thing to Done. Here's an honest look at where each one is stronger.

Weft is the app on this page most like Done. It's an AI task board for solo founders and small teams: your AI connects over MCP with OAuth 2.1, claims tasks from a Scrumban board with one active sprint, and can stop to ask you a question or record a decision. It has 32 MCP tools, apps for iPhone and Android, and an interface in about 27 languages. So the difference isn't whether agents can work your tasks. It's the shape of the loop: in Done, agent-finished work always waits for your approval unless you let the agent finish that task on its own, agents work in named lanes and hand off to each other, and Plan my day fits your tasks around your calendar. Weft is board-and-sprint first; Done is list-and-approval first.

FeatureDoneWeft
Assign a task to an AI agent that does the workYesAgents claim tasks from the board over MCP
Agent work waits for your approval before it counts as doneYesAn agent can send finished work to your review queue
An agent can stop and ask you a question, then carry onYesYes, and decisions are recorded
Several named agents, each with its own queueYesEach connected client sees the work assigned to it
Official MCP server for your AI agentsYesOfficial hosted server, 32 tools, OAuth 2.1
Agents read your connected apps for context (Drive, Gmail, Notion, GitHub…)YesNot documented
Natural-language quick captureYesThrough your AI, including bulk creation
Auto-decompose a task into subtasksYesNot documented
Recurring tasksYesNot documented
Task dependencies (blocked-by)YesNot documented
Goals that show whether you're on paceYesNot documented
Time-blocks your day around your real meetings, and re-plans when one movesYesNo calendar; due dates only
Describe a filtered view in a sentenceYesNot documented
Daily digest of overdue / due-today / stalledYesA board briefing your AI can read
PriceFree (100 agent calls/mo); Pro $5/moFree (50 tasks, 200 AI calls/mo); Pro $5/seat/mo yearly, $7 monthly

Weighted scorecard

Each product gets a score from 0 to 5 on eight criteria, with a one-line reason. The weights say how much each criterion counts, and the total is the weighted average, out of 5.

The default weights reflect a buyer handing work to AI agents, the person Done is built for, so they favour Done. Pick another buyer and the weights change: for a team running sprints, or for a personal list without AI, other apps often come out ahead.

Weights for

For someone who delegates tasks to Claude, ChatGPT or other agents and wants to approve what comes back.

DoneWeft
Hand a task to any AI agent (MCP, OAuth)Weight 25%
86 MCP tools over OAuth or a per-account token; any task can be assigned to an agent32 MCP tools over OAuth 2.1; agents claim tasks from the board
Human approval before agent work counts as doneWeight 20%
Agent-finished work waits for your approval by default; nothing closes without youAn agent can send finished work to your review queue, but it's the agent's choice
Agent questions, decisions and several named agentsWeight 15%
Agents park questions for you, and named agent lanes hand work to each otherAgents ask you questions and record decisions; no named agent lanes documented
Planning against your calendarWeight 5%
Plan my day time-blocks tasks around Google Calendar and re-plans; no team schedulingDue dates only; no calendar
Team projects and sprintsWeight 5%
Shared workspaces and per-project sharing on Teams; no sprints, timelines or workload viewsScrumban with one active sprint, invites and roles on Pro
Personal list: capture, recurring tasks, remindersWeight 10%
Natural-language capture, recurring tasks, dependencies and a daily digestBoard-first; capture goes mostly through your AI, no recurring tasks documented
Apps on phone and desktopWeight 10%
Web, iPhone, iPad, Android, and Apple silicon Macs via the iPad app; no Windows appiPhone and Android (offline-first) and the web; desktop app in the works
Price for one personWeight 10%
Free with 100 agent calls a month; Pro $5/mo, Teams $20/moFree (50 tasks, 200 AI calls/mo); Pro $5/seat/mo yearly
Weighted total
4.6 /53.9 /5

Scores are our judgment from each vendor's public docs and pricing, checked on the date at the foot of this page. Anything a vendor doesn't document scores 0.

Who Weft is for

Weft is for solo founders and small product teams who think in a kanban board with sprints, want their AI to pull work from that board, and value a lean tool with a generous free plan and offline-first mobile apps.

Why people choose Done

  • An approval gate by default: agent-finished work waits for you unless you let it finish that task on its own
  • Named agent lanes with handoffs, so a research agent can pass work to a writing agent
  • Plan my day time-blocks your tasks around Google Calendar and re-plans when a meeting moves
  • Dependencies, recurring tasks, goals and connected apps your agents can read for context

Where Weft shines

Weft is a genuinely well-thought-out agent board. Agents claim a task so two of them never pick up the same one, they keep the claim alive while they work, they can ask you a question without losing their place, and their decisions are written down for the next session. Scrumban with a single active sprint gives a small team just enough structure, the mobile apps work offline, and Pro is cheap per seat.

Frequently asked questions

Weft's agents can ask questions too. What's actually different?

You're right, both do. In Weft an agent calls request_input and keeps its claim on the task until you answer; in Done an agent parks a question with ask_decision and moves on to other work. The bigger differences are elsewhere: Done holds every agent-finished task for your approval by default, while in Weft sending work to your review queue is an option the agent can take; Done has named agent lanes with handoffs; and Done plans your day against your calendar, which Weft doesn't do.

Does Done have sprints like Weft?

No. Done has a board whose columns can be status, priority or project, plus dependencies and goals, but no sprints. If time-boxed sprints are how your team works, Weft's Scrumban fits that better.

How do the prices compare?

They're close. Weft's free plan has 50 tasks on the board and 200 AI calls a month (unlimited for the first 48 hours), and Pro is $5 per seat a month billed yearly or $7 monthly. Done's free plan has 100 agent calls a month and two workspaces, Pro is $5 a month, and Teams is $20 a month.

Try the AI to-do app for yourself

Sign up with just an email, capture a task, and assign it to an AI agent.

Comparison based on publicly available information last verified in October 2026. Weft and other names are trademarks of their respective owners; features change — check their site for the latest.