An AI you ask to do work, or a system that acts on what arrives.
Town is a polished personal AI agent. Multi-surface, with routines, three approval modes per tool, and a Memory Profile that learns your voice and priorities. You go to Town, ask it to do something, it does it. this+that is different. It's a comms-forward AI that reads the messages you receive whether you asked for them or not, scans every email and chat for what needs doing, and acts on what shows up. Two different shapes of AI for work, not really direct alternatives.
A polished personal agent, or a comms-forward AI for your messages
AI assistants come in different shapes. We think of three waves: Wave 1 is the general-purpose chat you open and ask (Claude, ChatGPT, Gemini, Copilot). Wave 1.5 is the polished personal agent layered on top of chat. Wave 2 is the fit-for-purpose AI that owns one job end-to-end, with UI tailored to it (more in our essay on AI's second wave).
Town sits in Wave 1.5, the polished personal-agent tier between raw chat and fit-for-purpose Wave 2 products. It wraps general-purpose models in routines, multi-surface presence, three approval modes per tool, and a Memory Profile that learns your voice and priorities. OpenClaw is the largest Wave 1.5 product by traction; Town, Manus, and Lindy are the other notable names. These products are closer to fit-for-purpose than vanilla chat, but they are still chat-shaped at the core. You still go to them and ask. this+that is one of Wave 2's first products. The agent reads the messages you receive whether you asked for them or not. Every email, Slack thread, Teams chat, Google Chat room, and Telegram message gets scanned for what needs doing, surfaced as tasks for the whole team, and runs through workflows. Most people who use Town would also benefit from a Wave 2 product handling their inbox. They solve different problems.
Feature by feature
How the two products compare across the things that matter most.
| Topic | Town | this+that |
|---|---|---|
| Category | Wave 1.5. Polished personal agent with routines and multi-surface presence, wrapping a general-purpose model. Same shape as OpenClaw and Hyperagent. | Wave 2. Fit-for-purpose AI that lives inside the work surface, acting on messages that arrive without you asking. |
| Where work starts | With you. You ask Town to do something, it does it. Plus a few proactive routines (news, calendar, inbox) you configure. | With incoming messages. The agent reads what arrives without being asked and surfaces what needs doing. |
| Email providers | Gmail (as a delegation surface). | Gmail and Outlook, continuously scanned for tasks and workflow triggers. |
| Messaging channels | Slack, WhatsApp, Telegram — primarily as places to talk to Town from. | Slack, Microsoft Teams, Google Chat, and Telegram — every message scanned for what needs doing. Instagram and Facebook Messenger awaiting approval. |
| Task extraction from messages | Not a focus. Tasks come from you delegating to Town, not from messages arriving. | Core capability. DoBox scans every message across every channel for requests, commitments, deadlines, and follow-ups, surfaced as assignable tasks for the team. |
| Memory / knowledge | A personal Memory Profile that learns your voice, preferences, and priorities over time. Single-user. | The brain — a writable team knowledge layer with personal and team spaces. Agents read and write. Pages can be published outward through public artifacts. |
| Workflow automation | Routines — scheduled or on-demand workflows (email triage, meeting prep, news digest) with three approval modes per tool. | Plain-language workflow builder. 32 action types. IF/ELSE branching, loops, and sub-agents. Triggered by messages or schedules. |
| Team capabilities | Single-user focused. Memory Profile, routines, and credits are per-user. | Team task assignment, shared task view, and team-request grounding (your agent searches a teammate's brain to draft a suggested reply). |
| Integrations | 34+ direct integrations including HubSpot, Salesforce, Asana, Linear, GitHub. | Open MCP standard. Any tool with an MCP server or API plugs in. |
| Trust controls | Three modes per tool: read-only, approval-required, autonomous. "A dial, not a switch." Full action logs. | Approval gates on every workflow action. Drafts not sends by default on outbound. Provenance: every task links back to the source message. |
| Pricing | Free (30 chats/month), Starter $15/mo, Pro $49/mo annual ($59/mo monthly), Power $99/mo annual ($119/mo monthly), Power Plus $199/mo annual ($239/mo monthly). Credit-based usage per plan. Per-user. | Free during beta. |
- Town does Wave 1.5 well. If what you want is one polished general-purpose AI you delegate work to (drafts, scheduling, research, routines), Town is one of the more thoughtful takes on it.
- The Memory Profile is a careful personalization layer for individual use: voice, priorities, and the people who matter, sharpening over time.
- Three approval modes per tool (read-only, approval-required, autonomous) is an elegant trust model. "A dial, not a switch" captures it well.
- Multi-surface availability — web, email, Slack, desktop, iOS, WhatsApp — means the same agent context follows you everywhere.
- Clear personal pricing: a Free tier for trying, $15/mo Starter, scaling to $199/mo Power Plus. Credit-based usage per plan.
- Transparency commitments stated up front: no model training on your data, full action logs.
- A different category. The agent reads the messages you receive — email, Slack, Teams, Google Chat, Telegram — and acts on them without you asking. Instagram and Facebook Messenger awaiting approval.
- DoBox: every message scanned for tasks, with the whole team able to see, assign, and track them in one place.
- Plain-language workflow builder triggered by incoming messages. 32 action types, branching, loops, sub-agents.
- The brain is a writable team knowledge layer that agents read and update as a side effect of doing real work.
- Open MCP, not a fixed integration list — any tool with an MCP server or API plugs in.
- Team-first design: task assignment, shared views, and team-request grounding are first-class capabilities, not personal features.
See what's waiting in your inbox
Connect your inbox and get a free analysis of the tasks, follow-ups, and open commitments this+that would surface across your channels.
Free to use · No credit card required