# Lindy — Slack-native AI teammate that connects to company tools and does delegated work, billed per seat with pooled credits. > Source: The Agents Index — https://theagentsindex.com/lindy (structured, researched, re-verified) > Facts last verified: 2026-09-19 Lindy is an AI teammate that lives in a company's Slack and connects to 1,000+ tools, meetings and files to carry out delegated work. It also runs in a web app, a Gmail Chrome extension and iMessage, and builds hosted dashboards and apps. | Fact | Value | | --- | --- | | Website | https://www.lindy.ai | | Price | from $29.99/month | | Free trial | Partly | No standing $0 plan. A 7-day free trial applies only to someone who first @mentions Lindy in their team's Slack; direct signups and people who join by signing up are billed right away. The free week is one-time per teammate, and a returning teammate goes straight onto a billed seat. ## What it does **Writes code** · Partly — Code authoring is a separate product line, Lindy Build, which generates full-stack apps from a description; the Slack teammate itself is sold for business work, not for writing software in your repository. > Build apps as powerful as they are beautiful, with frontend, backend, databases, and integrations fully built in. > — https://www.lindy.ai/app-builder · Features section, 'Full-stack builds' card **Debugs and fixes** · Partly — Lindy Build runs QA agents that exercise the app it generated and repair what they break, so debugging is scoped to Lindy's own generated app rather than to an existing customer codebase. > Skip tedious debugging with QA agents that click through your app and fix broken code. > — https://www.lindy.ai/app-builder · Features section, 'Continuous QA' card **Writes tests** · Partly — QA agents exercise the app in a browser; the vendor never claims it produces test code you keep > Skip tedious debugging with QA agents that click through your app and fix broken code. > — https://www.lindy.ai/app-builder · Features section, 'Continuous QA' card **Reviews code** · Partly — Code review appears only as a listed engineering use case for the Slack teammate; Lindy documents no diff or pull-request review surface, review policy, or per-PR workflow anywhere in its docs. > Ticket triage, bug investigation, code review, oncall. > — https://docs.lindy.ai/use-cases · Engineering section, subtitle under the heading **Ships it** · Partly — Lindy ships what it builds to its own hosted lindy.link URL and rebuilds on the same address, so work reaches an audience without a deploy step, but it does not deploy into your own infrastructure. > It builds the thing, hosts it, and gives you a link on its own lindy.link address. > — https://docs.lindy.ai/teammate/artifacts · Opening paragraph, above 'Every artifact starts private' **Done-for-you service** · No — This is self-serve software you run yourself: sign up, install the Slack app, connect tools. The only human service published is onboarding and enablement, and that starts on Pro. > Live onboarding on Pro and up > — https://docs.lindy.ai/teammate/lindy-teammate-billing · 'What every plan gets' section, bulleted list of plan-dependent items _Not established: Whole-codebase work_ ## How much it does unattended **Runs autonomously** · Partly — Routines run on a schedule or trigger with nobody present, and Lindy pulls data and drafts on its own, but its docs state that actions which write or send stop for a human approver first. > set a schedule or trigger once, and Lindy runs the whole job for you on autopilot > — https://docs.lindy.ai/teammate/routines · Introductory paragraph under the 'Routines' heading **Multi-agent** · Partly — Lindy Build pairs the builder with separate QA agents working the same app; the Teammate product gives each person a private Lindy plus one shared team Lindy, and the vendor describes no orchestration between them. > Skip tedious debugging with QA agents that click through your app and fix broken code. > — https://www.lindy.ai/app-builder · Features section, Continuous QA card **Agent permissions** · Yes — Every connected account carries a guardrail of Always allow, Require approval or Don't offer, and reads are never gated. Approval is enforced in shared Slack threads, while DMs and web chat are not. > Each connected account has one setting: Always allow or Ask for approval, applied to every action that writes or sends. Read-only actions never need approval. > — https://docs.lindy.ai/teammate/setup · 'Guardrails and approvals' section ## Which models it runs on **Claude** · Yes — Anthropic models are named on the enterprise page as selectable per job, and Lindy's billing docs say every plan, including trial seats, gets every model with no upsell wall. > Anthropic, OpenAI, Gemini and the top frontier models. Pick the right one per job, and control access. > — https://www.lindy.ai/enterprise · Enterprise features section, 'Models without lock-in' card **GPT** · Yes — OpenAI is named alongside Anthropic and Gemini as a model family a user picks per task, and model choice is not gated by plan according to Lindy's billing documentation. > Anthropic, OpenAI, Gemini and the top frontier models. Pick the right one per job, and control access. > — https://www.lindy.ai/enterprise · Enterprise features section, 'Models without lock-in' card **Model choice** · Yes — The buyer picks the model per task from a dropdown and can set a default, and Lindy also picks one itself to control credit spend; no tier restricts which models are reachable. > Every plan, trial seats included, gets all models. There's no upsell wall on model choice. > — https://docs.lindy.ai/teammate/lindy-teammate-billing · 'What every plan gets' section, opening line _Not established: Open models_ ## Where you use it **In your editor** · No — The documented surfaces are Slack, the chat.lindy.ai web app, iMessage and SMS, and a Chrome extension that works only inside Gmail. No editor or IDE plugin appears anywhere in the docs. > The Chrome extension is currently Gmail only. Outlook is coming soon. > — https://docs.lindy.ai/features/chrome-extension · Note box under 'Lindy, Inside Gmail' **On the command line** · No — The nearest thing to a command line is a set of Slack slash commands for managing your connection and usage; Lindy publishes no terminal client, shell binary or local CLI. > Slash commands for managing your Lindy connection, context, and usage right inside Slack. > — https://docs.lindy.ai/teammate/slack-commands · Page subtitle under the 'Slack Commands' heading **In your pipeline** · No — GitHub is one of the 1,000+ integrations, but no pull-request or CI surface is claimed in the enumerated surface list > Works wherever you work > — https://docs.lindy.ai/index · 'Works wherever you work' section, pill list: Slack, iMessage, Chrome extension **In a browser** · Yes — chat.lindy.ai is the signed-in web application: a Home page with a chat box, meetings, routines, files, settings and billing, and the account the Chrome extension signs in against. > Home isn't a dashboard of buttons to configure. It's where you talk to Lindy and see what it's been doing for you. > — https://docs.lindy.ai/teammate/home · Paragraph under the 'Home' heading ## Whose machine it runs on **Self-hosted** · No — Lindy runs only on the vendor's own cloud. Nothing in the plan comparison offers a customer-hosted deployment, and even Enterprise adds governance controls rather than an infrastructure option. > Lindy runs on enterprise-grade cloud infrastructure with hardened access controls. Your data doesn't mingle with anyone else's. > — https://www.lindy.ai/security · 'Under the hood' section, Infrastructure card **Open source** · No — No repository or source availability anywhere on the site; the product is described only as vendor-run cloud infrastructure > Lindy runs on enterprise-grade cloud infrastructure with hardened access controls. Your data doesn't mingle with anyone else's. > — https://www.lindy.ai/security · 'Under the hood' section, Infrastructure card ## What it costs to run **How it meters** · Yes — Two meters run at once: a per-user seat price, and credits consumed only while Lindy works, priced at roughly a cent each with published bands of 2-250, 250-1,000 and 1,000-2,500 per job. > Credits measure the work Lindy does, about one cent each. You only spend them when Lindy is actually working, and bigger jobs use more. > — https://docs.lindy.ai/pricing · 'What's a Credit?' section **Free tier** · Partly — There is no standing free plan. A free first week exists only for someone who joins by @mentioning Lindy in a team Slack; anyone signing up directly is billed immediately, and the week is one-time per person. > The free week applies to the Slack path. Direct signups and people who join by signing up are billed right away. > — https://docs.lindy.ai/teammate/lindy-teammate-billing · Note box under 'How someone becomes a seat' **MCP server** · Partly — MCP runs inbound only: you point Lindy at a hosted MCP server and it builds an action per published tool, with per-connection sharing and approval settings. Lindy publishes no MCP server of its own for another agent to query. > Point Lindy at a hosted MCP server and it builds actions from the tools that server publishes. > — https://docs.lindy.ai/integrations/mcp · Page subtitle under the 'MCP servers' heading **Bring your own key** · Partly — You can store your own third-party API keys as credentials that Lindy uses when running shell commands and code, but inference is bought through Lindy credits: no bring-your-own model key or own-cloud option is published. > Credentials are what Lindy reaches for when it runs shell commands and code. > — https://docs.lindy.ai/integrations/credentials · Paragraph above 'Adding a credential' _Not established: API access_ ## Buying it for a team **A company can buy it** · Yes — The unit of sale is a workspace, not an individual: one subscription, one bill, member and admin roles, an owner who holds payment and deletion rights, and admin-set credit allocations. > Teammate is one workspace subscription: every seat is on a single bill and all credits pool together. > — https://www.lindy.ai/pricing · FAQ, 'How does billing and seat management work?' **Seat model** · Yes — Priced per user at 29.99, 99.99 or 199.99 dollars a month with no published seat floor or ceiling; a seat is taken by anyone who uses Lindy, stays billed until an admin removes it, and is not prorated mid-cycle. > Anyone who uses Lindy takes a seat, whether they sign up directly, join your workspace, or @mention Lindy in Slack. > — https://www.lindy.ai/pricing · FAQ, 'Who actually needs a paid seat?' **Pooled budget** · Yes — One balance for the whole workspace: each seat contributes its allocation, the shared and personal Lindys both draw from it, and admins can cap an individual's draw or leave it unlimited. > Credits are pooled at the workspace level. Each seat adds its plan's allocation to one shared balance the whole team draws from, and admins can cap how much any one person pulls. > — https://docs.lindy.ai/pricing · 'How Credits Work Across a Team' section **Admin controls** · Yes — Admins toggle meeting recording, email drafting and triaging workspace-wide, set per-member credit limits, choose which channels and folders Lindy may draw on, and decide which integrations write without asking. > Admins can control which features are available to users across the workspace. > — https://docs.lindy.ai/start-here/team-setup · 'Admin Controls' section **Audit log** · Partly — Lindy says every action it takes is logged and visible, but audit logs as an administrative feature are named only in the Enterprise column of the plan table and the Enterprise-only list in the docs. > SSO, SCIM, audit logs, and HIPAA/BAA on Enterprise > — https://docs.lindy.ai/teammate/lindy-teammate-billing · 'What every plan gets' section, first plan-dependent bullet **Single sign-on** · Partly — Single sign-on with SCIM provisioning is an Enterprise-only line, marked absent on Plus, Pro and Max in the comparison table. Lindy never names the protocol, so SAML versus OIDC is unstated. > Access through your identity provider, with user provisioning from a single source of truth. > — https://www.lindy.ai/enterprise · Enterprise features section, 'SSO & SCIM' card ## What happens to your code **Opt out of training** · Yes — Training exclusion is the default rather than a setting to find: Lindy states neither it nor its model providers train on customer data, and repeats the claim in its docs and pricing FAQ. > Lindy does not sell your data. Lindy and our providers do not use your data to train AI models. > — https://www.lindy.ai/security · 'Data Governance & Privacy' section, Data Protection card **Data residency** · Partly — The vendor says residency requirements are supported but names no region, jurisdiction or hosting provider anywhere on the site or in the docs, and offers no self-hosted alternative. > You control how your data is processed and stored. Data deletion requests, access rights, and residency requirements are all supported. > — https://www.lindy.ai/security · Data Governance & Privacy section, Privacy Controls card **Getting out** · Partly — Unused plan credits expire every cycle while purchased top-ups carry over, and deletion and access rights are offered; we found no documented bulk export, and cancelling leaves the workspace live only to the end of the paid cycle. > Your plan's credits refresh at the start of each billing cycle and don't roll over, so every month starts fresh. Purchased top-up credits are the exception: they carry over and don't expire. > — https://docs.lindy.ai/pricing · FAQ, 'Do unused credits roll over?' **Certifications** · Yes — SOC 2 Type II audited by Johanson Group, plus GDPR, HIPAA and PIPEDA, with a Trust Center for reports; the signed BAA for HIPAA is reserved for the Enterprise plan. > Lindy is AICPA SOC 2 Type II, GDPR, HIPAA, and PIPEDA compliant. > — https://docs.lindy.ai/resources/security · Opening line of the Security page ## Provenance Every fact above comes from the vendor. Nothing here is independently corroborated yet. ## Coverage elsewhere Pages about this product that the vendor does not control. The label states how independent each one is. | Source | Kind | Read | | --- | --- | --- | | g2.com | Review platform | 2026-08-24 | | trustpilot.com | Review platform | 2026-08-24 | ## What changed - 2026-09-19 — Capabilities · Commercial terms · Free tier - 2026-09-02 — Commercial terms · Free tier · Price - 2026-08-31 — Capabilities · Commercial terms · Free tier · Price - 2026-08-23 — Alternatives · Documentation link · LinkedIn link · One-liner · Summary ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Lindy, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth. Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.