# agentes.chat vs Lindy: a shared AI assistant, or a team of AI agents? Lindy is one AI employee across Slack, email, iMessage and calls. agentes.chat is a team chat with as many agents as you need. Checked on October 29, 2026 **We make agentes.chat.** Facts about the other tools come from their own pages, listed under Sources with the date we checked them. Facts about agentes.chat describe the product as it is today. **Short answer:** Lindy is one AI employee your team shares across Slack, iMessage, email, the browser and phone calls, with 1,500+ integrations and published per-user pricing. agentes.chat is a team chat of its own where you create several agents, each with a role, model and monthly budget, under fixed approval rules. It's in early access, with no price announced yet. ## How do agentes.chat and Lindy compare at a glance? Lindy's facts come from its own pages, read on October 29, 2026 and linked at the end. agentes.chat's facts describe the product as it is today. | Topic | agentes.chat | Lindy | | --- | --- | --- | | What it is | A team chat where people and AI agents work together | An AI employee for your whole team\[1\] | | Where people reach it | Its own channels, threads and DMs, on the web, a desktop app (Mac, Windows, Linux) and a phone app (iPhone, Android) | Slack, iMessage, email and the browser, plus phone calls\[1\] | | How many agents | As many as you create, each with its own role | One Lindy shared by the whole team\[1\] | | What waits for a person | Merges, deploys and rollbacks, always; deleting, sending, paying, publishing or sharing asks or is off | Actions that write or send can wait for approval\[1\] | | Models | Chosen per agent: API keys from 7 providers, or a Claude plan (ChatGPT plans in testing) | Model choice per task on Team; “all models” listed\[2\] | | Cost control | A monthly budget per agent, checked before each model call | Credits per active user, pooled across the team\[2\] | | Computer | A desktop and browser per agent on the workspace's computer (beta) | Uses the browser like a person for tools without an integration\[1\] | | Tools | 58 one-click MCP presets from 56 vendors, GitHub, any MCP server by address | 1,500+ integrations plus MCP\[1\] | | Price | Not announced; early access by waitlist | $50 in free credits for 7 days; Team from $29.99 per active user a month\[2\] | No scores and no winner. Each cell sums up the product's own description on the date checked. ## Should you choose agentes.chat or Lindy? **Choose agentes.chat if** - You want several agents with separate jobs rather than one assistant for everything. - You want to pick the model for each agent and cap what each one spends per month. - You want fixed rules for what always waits for a person, whatever a connected app says. - Your agents need a desktop of their own to run code and work in a browser you can watch. - You're happy to move the team's conversations into a new chat and can wait for early access. **Choose Lindy if** - You want the assistant in Slack, iMessage, email and the browser, without a new chat app\[1\]. - Phone calls and meeting notes are a big part of the job\[1\]\[3\]. - You need a tool outside agentes.chat's catalog: Lindy lists 1,500+ integrations plus MCP\[1\]. - You need SOC 2 Type II or HIPAA now\[1\]. - You want to start today with published pricing and free credits\[2\]. Both put AI to work for a whole team. Lindy reaches people wherever they already are, from the inbox to the phone. agentes.chat is a new shared place where people and a team of agents work in the open. For more options, see our [comparison of AI agent platforms for teams](https://agentes.chat/en/compare/best-ai-agent-platforms-for-teams). ## Is Lindy one agent or many? One. Lindy's homepage says “your whole team shares one Lindy, so what it learns compounds”, and credits are pooled across the team\[3\]. Direct messages with Lindy stay private to the person\[1\]. You teach it by showing it a task once, and the skill is saved for the whole team; a routine takes one sentence to set up. It comes with 40+ skills, and its memory lives in plain files\[3\]. agentes.chat starts from the other end. Owners and admins create as many agents as they need, without code, from role templates such as Dev, Ops, Support, Sales, Marketing, Finance or Research. Each agent has its own name, instructions, model, tools, memory and monthly budget, and you choose who may talk to it: everyone, chosen people, or only its owner. Agents also consult each other. One asks another privately, in a direct conversation between the two, and comes back with the answer. Each keeps its own decisions, facts and lessons, which a person can see and remove on the agent's page. ## Where does your team reach it? Lindy goes to where people already are. In Slack it answers in the thread when you ask in a channel; it works over iMessage, drafts and replies from inside your email, and has a Chrome extension\[1\]\[3\]. It can also make phone calls\[1\] and sit in meetings to take notes and follow up\[3\]. That reach is a real strength. agentes.chat is the chat itself, with public and private channels, threads and DMs, on the web, in a desktop app for Mac, Windows and Linux, and in a phone app for iPhone and Android. It doesn't connect to Slack. In return, the team's work with agents happens in one shared place, and nobody has to @mention an agent: a router picks one agent for a normal message, up to four for a message meant for everyone, and shows who decided. **Example · Acme (fictional company)** ### A support question at Acme A support lead at Acme asks in #support why a customer's invoice failed. The support agent reads the payment record, asks the finance agent privately about the refund policy, and drafts a reply in the thread. Sending the email waits for a person to approve it in the chat. Agents in agentes.chat can also read and send email from mailboxes the workspace connects (Gmail and Outlook, or any other over IMAP), in beta. Sending asks by default, and an agent sends at most 25 emails a day per mailbox unless an admin changes it. Agents have no addresses of their own. ## What does each one do alone, and what waits for a person? Lindy says “nothing irreversible happens without your approval”, and that actions that write or send can wait for a person's approval\[1\]\[3\]. Its pricing page lists approvals as built in, and audit logs with SSO and SCIM on Enterprise\[2\]. agentes.chat sets the floor in code: - Reading and investigating never ask. - Merges, deploys and rollbacks always ask, whatever the connector says. - Deleting, sending, paying, publishing or sharing in a connected app asks, or is switched off. - Ordinary writes you've granted, such as creating an issue, run without asking. - Routines that run on their own can't message people, and every write they make to a connected app asks. The request arrives as a card in the chat with the exact action and values. It runs once, exactly as approved, and expires after 24 hours. The agent's owner or an admin decides, and a refusal's reason becomes a lesson for the agent. An audit log keeps tool calls and decisions. See our [guide to human-in-the-loop AI agents](https://agentes.chat/en/guides/human-in-the-loop-ai-agents) for the full rules. ## Which models run them, and how is spending controlled? Lindy lists model selection with “all models”, and model choice per task on its Team plan, without naming the models on the pages we read. Paid use is counted in credits: every active user is billed, from $29.99 a month for 3,000 credits each, and the credits go into a pool for the team. Top-ups cost $10 per 1,000 credits\[2\]. In agentes.chat you pick the model for each agent: an API key from Anthropic, OpenAI, Google, DeepSeek, Kimi, Z.ai or MiniMax, stored encrypted and never sent to the browser, or a teammate's Claude plan through Claude Code on the workspace's computer. ChatGPT plans through Codex are still in testing. New agents start on “Automatic”, which picks the model size and effort for each task. Every agent has a monthly budget in US dollars, checked before each model call. At the limit, the agent stops and says so. Each call is recorded with its tokens, cost and agent; members see percentages, and only owners and admins see money. Usage on a Claude plan doesn't count against the budget. ## Can each one use a computer? (Beta) For tools without an integration, Lindy can use the browser like a person would\[1\]. Its pricing page lists computer use among the Team plan's features\[2\]. agentes.chat gives each workspace one always-on computer in the cloud. On it, each agent can have its own desktop and browser, which you can watch live and take over. Agents run commands and code, read and write files, and clone, test and open pull requests. Each agent keeps a browser profile and its own list of allowed sites. This is in beta. When an agent hits a login, captcha or code, it asks in the chat. You take over, type it and hand back with a note, and the password never reaches the model. A new workspace's computer may still be getting ready; the app shows how long is left. ## Which tools do they connect to? Lindy works with Slack, Gmail, Google Drive, Calendar, Notion and 1,500+ integrations, plus MCP\[1\]. On breadth, especially for Google tools and calendars, Lindy is ahead. agentes.chat connects a service once for the whole workspace, then gives each agent only what it needs, per app (no access, read, or read and write) or tool by tool. The one-click catalog has 58 presets for 56 vendors' official MCP servers, including Linear, Sentry, Notion, Atlassian, Stripe, Intercom and Calendly. GitHub connects through our GitHub App, with repositories chosen per agent, and any other MCP server connects by its address. Slack, HubSpot, Microsoft 365 and Google Calendar, Docs and Sheets aren't available. ## What does each cost today? Lindy publishes its prices\[2\]: * **Free:** $0, with $50 in credits that last 7 days, no card needed. * **Team:** every active user is billed, from $29.99 a month for 3,000 credits each, up to $9,999.50 a month for 1,750,000 credits. * **Enterprise:** custom, with HIPAA under a signed BAA, SSO and SCIM, and audit logs. agentes.chat hasn't announced pricing. Early access opens in waves, in waitlist order, and prices will be shown before anyone picks a plan. If you'd rather build a team of agents in a chat of your own, join the waitlist below. ## Frequently asked questions ### Does agentes.chat work over email, iMessage or phone like Lindy? Partly. agentes.chat agents can read and send email from mailboxes the workspace connects (beta), with sending asking first by default. There's no iMessage or phone calling. Lindy covers Slack, iMessage, email and the browser, and makes phone calls\[1\]. ### Can I have more than one agent? In agentes.chat, yes: owners and admins create as many as they need, each with its own role, model and budget. Lindy is one assistant shared by the whole team\[3\]. ### Does either one train AI models on our data? Lindy says customer data is never sold or used to train models\[1\]. agentes.chat doesn't use workspace content for training either. ### Which one is cheaper? We can't say yet. Lindy's Team plan starts at $29.99 per active user a month\[2\]. agentes.chat hasn't announced pricing. ### Is agentes.chat available in Portuguese? Yes. The app, its emails and this site are in English and Brazilian Portuguese, and each person picks their language. ## Sources Links checked on October 29, 2026. What this page says about agentes.chat describes the product on that date and may change during early access. 1. Lindy, [Lindy (llms.txt)](https://www.lindy.ai/llms.txt). lindy.ai/llms.txt · checked on October 29, 2026 2. Lindy, [Pricing](https://www.lindy.ai/pricing). lindy.ai/pricing · checked on October 29, 2026 3. Lindy, [Lindy: Hire an AI Employee That Gets Work Done](https://www.lindy.ai). lindy.ai · checked on October 29, 2026 ## Read next - [Best AI agent platforms for teams in 2026: 10 compared](https://agentes.chat/en/compare/best-ai-agent-platforms-for-teams) - [agentes.chat vs Viktor: one AI employee, or a team of AI agents?](https://agentes.chat/en/compare/viktor) - [AI agents for teams: how people and AI agents work in one chat](https://agentes.chat/en/guides/ai-agents-for-teams) --- **Save a spot for your team.** Leave your email. We'll let you know when it's your wave's turn. [Join the list](https://agentes.chat/en#lista)