Lindy
Also known as: Lindy Teammate, Lindies, Autopilot, Lindy Academy
AI teammate that lives in Slack, answers from your tools and meetings, and runs multi-step work with approvals built in.
Lindy is an AI teammate that lives in a company's Slack workspace, where everyone gets a private assistant in their DMs and the whole team shares one in channels. Rather than asking users to build automations, it is designed to be delegated to in conversation: ask a question and it answers from your tools and meetings with the underlying file or decision attached, hand it a task and it runs the multi-step work across systems from start to finish, or ask for an artifact and it produces decks, sheets and reports.
The product is organised around five capabilities. It connects to Gmail, Slack, Notion, HubSpot and over a thousand other tools plus any MCP server, and where no programmatic interface exists it can drive a cloud computer directly. It joins meetings on Google Meet, Zoom and Teams as a visible participant, then records, transcribes and files them into a searchable library of shareable folders.
Routines carry recurring work on a schedule, from morning briefs to weekly reports. It ships with more than forty skills covering research, analysis, decks and dashboards, and a team can add their own by demonstrating a task once. Its memory lives in a versioned plain-file system the customer can open, read and edit like a document, split between personal and workspace scope.
Oversight is default-on rather than optional. Anything with outside impact, sending an email, updating a ticket, posting to another channel, publishing a document, waits for a named approver, while read-only lookups from approved sources proceed. Permissions are set per integration and revocable, private Slack channels are reachable only by invitation, and personal DMs, email and meetings never surface in shared channels.
Pricing is per seat with a shared credit pool the whole workspace draws from, starting at $29.99 per user per month. The platform is model agnostic, letting the customer pick a model per task, and carries SOC 2 Type II, GDPR, HIPAA and PIPEDA, with SSO, SCIM and audit logs on the Enterprise tier. It is delivered as managed SaaS only, with no self-hosted, VPC or region-selection option.
Vendor details
Canonical URL
https://www.lindy.ai
Category
Agent builder
Subcategory
Slack-resident AI teammate with meetings, routines, skills and editable file-based memory
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Connects to Gmail, Slack, Notion, HubSpot and 1,000+ tools, plus any hosted MCP server, from which it builds actions out of the tools that server publishes. A credentials vault stores an API key once for personal or workspace use without pasting it into a chat, and per-integration guardrails control what Lindy may do with each connection. An HTTP Request skill covers anything uncatalogued, and a Pipedream partnership contributed 500+ actions across 200+ apps. Where no interface exists at all, computer use gives the agent a cloud machine to drive the screen directly. Surfaces it works through: Slack threads and mentions, iMessage and SMS, Gmail via a Chrome extension, and Google Meet, Zoom and Teams, which it joins as a visible named participant to record and transcribe. Inbound programmatic invocation is via a bearer-token webhook trigger with callback response. Integration counts are self-inconsistent across the vendor's surfaces, 1,000+ on current pages against 3,000+ on legacy academy material.
In practice
Someone asks in #growth why signup conversion dropped. Lindy traces it across four tools to a broken verification step after Tuesday's deploy, writes up the root cause, files the ticket and flags the deploy in #eng.
A deal closes and the handoff needs doing. Lindy updates HubSpot, creates the Notion doc, posts to customer-success, schedules the kickoff and sends the welcome email, pausing for approval on anything that leaves the building.
You were out for a week. Lindy gives you the TL;DR of the busy channel, what was decided, and exactly what still needs you, drawing on meetings it recorded while you were away.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
The vendor states connections to Gmail, Slack, Notion, HubSpot and 1,000+ tools plus any hosted MCP server, from which Lindy builds actions out of the tools that server publishes; the integrations documentation adds a credentials vault so an API key is saved once and shared with the workspace without being pasted into a chat, and per-integration guardrails control what Lindy may do with each connection. An HTTP Request skill covers anything uncatalogued, and the changelog records 500+ additional actions across 200+ apps arriving through a Pipedream partnership. Legacy material claims 3,000+ integrations, against 1,000+ on the current pages. Sourcedocs.lindy.ai integrations, credentials and MCP pages, lindy.ai/changelogread 2026-08-31 |
|
| Workflow Orchestration | Full |
|
Multi-step work across tools start to finish is a headline documented capability, with a worked deal-won handoff running five systems in one run: update HubSpot, create the Notion doc, post to the customer-success channel, schedule the kickoff and send the welcome email. A worked investigation traces a metric across four tools to a root cause, writes it up, files a ticket and flags the deploy. Routines carry recurring multi-step work on a schedule, and skills act as reusable playbooks the agent selects on its own when a request calls for them. Multi-agent coordination appears only in the legacy builder material, where separate agents could work together, and not in the current product's documentation. Sourcedocs.lindy.ai index, routines and skills pagesread 2026-08-31 |
|
| Knowledge Grounding & RAG | Full |
|
Lindy records and transcribes meetings on Google Meet, Zoom and Teams and files them into a searchable library of shareable folders that can be queried later, with shared meeting library and folders included on every plan. Grounding also spans Slack history and connected tools, with the vendor stating answers come back with the underlying file or decision attached, and a versioned team file system holds documents Lindy works from. Ad hoc knowledge lookups are a documented delegation pattern, and persistent workspace context is an included capability. Sourcedocs.lindy.ai meeting-library, files and ad-hoc-tasks pages, lindy.ai/pricingread 2026-08-31 |
|
| Human Oversight & Guardrails | Full |
|
Approvals built in is listed among the capabilities included on every plan, and the vendor states across three first-party surfaces that nothing irreversible happens without approval: anything with outside impact such as sending an email, updating a ticket, posting to another channel or publishing a doc waits for a named approver, while read-only lookups from approved sources proceed without one. Integration-level guardrails control what Lindy may do with each connected tool, permissions are set, changed and revoked by the customer, and channel scope is explicit, with private Slack channels reachable only if a channel manager invites it. Sourcelindy.ai/pricing, lindy.ai/security and docs.lindy.ai integrations overviewread 2026-08-31 |
|
| Security, Identity & Governance | Full |
|
SOC 2 Type II certified with the audit attributed to Johanson Group, plus GDPR, HIPAA and PIPEDA, with a Drata-hosted trust centre for requesting reports and compliance summaries and a named security contact for architecture detail and penetration-test results. Named customer-facing controls: permissions the customer sets, changes and revokes per integration, encryption in transit and at rest, data never sold or used for model training, deletion and access rights, and on Enterprise SSO, SCIM, audit logs and a signed BAA. The vendor also states regular vulnerability scanning and penetration testing, real-time monitoring and a defined incident-response playbook. Sourcelindy.ai/security, lindy.ai/pricing and app.drata.com trust centreread 2026-08-31 |
|
| Observability & Auditability | Partial |
|
Team files carry version history and the meeting library is searchable and shareable, both included on every plan, but audit logs are listed only under Enterprise on the pricing page and no logging, tracing or audit documentation page exists anywhere in the complete Teammate documentation index. The security page asserts that every action is logged and inspectable including why, which the tiering contradicts. A per-run task view showing the received request body and how each action field was completed is documented, but only in the legacy builder documentation outside the current index. Sourcelindy.ai/pricing, lindy.ai/security, docs.lindy.ai index and docs.lindy.ai legacy webhooks pageread 2026-08-31 |
|
| Memory & State Persistence | Full |
|
Files is documented as a versioned file system the customer can see into, edit and share, containing the memory folder where what Lindy knows is kept in plain files that can be opened and changed like a document; the site shows retained facts such as recurring report timing and individual formatting preferences. Persistent workspace context and team files with version history are listed among the capabilities included on every plan, memory is scoped personal or workspace with personal context never surfacing in shared channels, and skills persist demonstrated procedures for reuse across the team. Sourcedocs.lindy.ai files and skills pages, lindy.ai/pricingread 2026-08-31 |
|
| Deployment & Data Residency | Unable to verify |
|
Managed SaaS only. The vendor states that data deletion requests, access rights and residency requirements are all supported, but names no region, no selection control and no deployment topology; infrastructure is described only as enterprise-grade cloud with hardened access controls and logical separation between customers. No VPC, on-premises, self-hosted, dedicated-cluster or region-selection option appears in the complete 27-page documentation index or among the eighteen capabilities the pricing page lists as included, and Enterprise adds identity, audit and BAA terms rather than any deployment choice. Sourcelindy.ai/security, lindy.ai/pricing and docs.lindy.ai indexread 2026-08-31 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
The product ships with 40+ skills covering research, data analysis, decks, dashboards and channel catch-ups, listed as 40+ skills plus create your own among the capabilities included on every plan, and documented as reusable playbooks the agent picks up on its own when a request calls for them. Customers add their own by showing Lindy a task once, after which it is saved for the whole team, and individual skills can be installed and toggled on or off. A creators programme publishes further material. Sourcedocs.lindy.ai skills page, lindy.ai/pricing and lindy.ai homepage skills panelread 2026-08-31 |
|
| Triggers & Channel Coverage | Full |
|
Schedules are covered by Routines, saved instructions that run recurring work automatically such as daily briefs, meeting follow-ups and weekly digests. Events include a reply being needed in the inbox, a meeting ending, time-sensitive mail triggering an outbound text alert, and a sent email going unanswered prompting a follow-up draft. Channels are Slack threads and mentions, iMessage and SMS, Gmail through a Chrome extension, and Google Meet, Zoom and Teams which Lindy joins as a named visible participant. Slack-native threads, scheduled routines and 24/7 iMessage are all listed as included on every plan. Sourcedocs.lindy.ai routines, iMessage, meeting-recording and chrome-extension pages, lindy.ai/pricingread 2026-08-31 |
|
| Model Flexibility & Routing | Full |
|
Model selection, all models is listed among the capabilities included on every plan, and the usage section states the product is model agnostic with the customer picking a model of choice for each task, most major models being available. The changelog corroborates an evolving multi-provider roster by recording individual models being added over time, including Gemini 2.5 Flash-Lite for phone calls and Gemini vision for shared images. Selection is per task rather than per workspace, so different work can run on different models within one seat. Sourcelindy.ai/pricing and lindy.ai/changelogread 2026-08-31 |
|
| APIs, SDKs & MCP Extensibility | Partial |
|
Inbound, the webhook trigger accepts a custom API call into a Lindy with a secret key sent as a bearer token in the Authorization header, exposes the received request body to downstream actions, and supports a callback action for two-way communication with the calling system; the changelog records the trigger's introduction and later support for custom headers and content types. Outbound, an HTTP Request skill calls arbitrary external APIs. No SDK, client library or Lindy-published MCP server was found; MCP appears only as Lindy consuming hosted servers, which is graded on Int. An OpenAPI specification is listed in the documentation index but was not retrievable this pass. Sourcedocs.lindy.ai webhooks page and documentation index, lindy.ai/changelogread 2026-08-31 |
|
| Testing, Debugging & Optimization | Unable to verify |
|
No testing, preview, sandbox, evaluation, scoring or benchmarking capability appears in the complete 27-page Teammate documentation index or in the eighteen capabilities the pricing page lists as included on every plan. The nearest documented affordances belong to the legacy builder rather than the current product: a task view for inspecting a completed run, configurable error-handling conditions after a webhook, and autosaved drafts with a discard-to-last-saved-version control. Routines and skills are authored in natural language and take effect directly, with no documented dry run. Sourcedocs.lindy.ai index, lindy.ai/pricing and lindy.ai/changelogread 2026-08-31 |
|
| Browser & Computer Use | Full |
|
Computer use is listed among the capabilities included on every plan. The vendor's changelog introduces the capability as Autopilot, stating that APIs are limiting and that the agent gets its own cloud computer and can do anything the user could do on theirs, and the site's own FAQ repeats that Lindy can use its computer or build its own integrations when a tool is not otherwise reachable. Sourcelindy.ai/pricing, lindy.ai/changelog and lindy.ai homepage FAQread 2026-08-31 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
Added Hunter, ContactOut, Prospeo integrations, and an Outlook Calendar trigger.
Bears on: Integrations
View sourceLindy added a Code action that runs custom Python or JavaScript directly within workflows.
Bears on: MCP / tool calling
View sourcePricing
From $29.99/user/mo
seats + shared credit pool
Included quota
Plus $29.99/user/mo: 3,000 credits per user per month, standard usage. Pro $99.99/user/mo: 15,000 credits per user per month, 5x Plus. Max $199.99/user/mo: 35,000 credits per user per month, ~12x Plus. Enterprise: custom, everything in Max plus HIPAA with a signed BAA, shared usage and bonus credits, dedicated support, audit logs, onboarding and enablement, with SSO and SCIM also named as Enterprise capabilities. Every plan includes the Slack-native teammate in threads and mentions, scheduled routines, persistent workspace context, 40+ skills plus custom ones, shared meeting library and folders, meeting recording, notes, scheduling, prep and follow-up, daily briefs and catch-ups, inbox management with replies drafted in the user's voice, up to 5 connected inboxes, 24/7 iMessage, team files with version history, computer use, thousands of integrations, MCP support, model selection across all models, and approvals. Credit guidance: everyday asks 2-250 credits, deep work 250-1,000, big builds 1,000-2,500.
What is public
Lindy (lindy.ai) sells Lindy Teammate on four tiers, three of them self-serve with list prices visible: Plus $29.99 per user per month with 3,000 credits, Pro $99.99 with 15,000, Max $199.99 with 35,000, and custom Enterprise adding SSO, SCIM, audit logs, HIPAA with a signed BAA, shared usage with bonus credits, dedicated support and enablement. There is no free tier; the only free access is a one-time seven-day week for a new teammate who joins via Slack. All eighteen core capabilities, including computer use, model selection, MCP support and approvals, are included on every paid plan, with the tiers differing on credits alone.
Billing mechanics
One workspace subscription billed per seat, with every seat's credit allocation pooled so the whole team draws from a single balance. Anyone who uses Lindy takes a seat, whether they sign up directly, join the workspace, or @mention Lindy in Slack. New teammates joining through Slack get a one-time seven-day free week before their seat is billed; direct signups are billed immediately, and a returning teammate does not get a second free week. Credits measure work rather than messages and scale with job size, from 2-250 for everyday asks up to 1,000-2,500 for complex builds. Credits refresh each cycle and do not roll over. Admins manage seats and per-seat credit allocations in one place.
Cost watchouts
Task credits, premium actions, model size, phone numbers, voice minutes
Variable cost rationale
Underlying credit/task metering, phone-number fees, and voice-minute costs can materially change production spend.
Additional watchouts
Lindy Phone adds explicit telephony cost. Each phone number is $10/month, and standard incoming/outgoing U.S. calls cost 20 credits per minute, with higher per-minute credit costs in some countries and call types. Support tiers also step up materially: help center/community for lower tiers, dedicated onboarding and support at Enterprise. [48]
Overage / add-ons
No overage billing on the pricing page: when the shared pool runs low Lindy pauses credit-using actions and notifies the workspace, with credits refreshing at the start of the next billing cycle and no rollover of unused credits; admins move to a higher plan for more. The homepage FAQ separately describes admin top-ups at $10 per 1,000 credits and per-seat credit allocations, which the pricing page does not repeat. Seats are removable at any time and stay active through the paid cycle with no mid-cycle proration.
Sales call required
No, self serve available
Free / trial
7-day trial
Lowest paid plan
$29.99/user/mo (Plus, 3,000 credits/user/mo)
Key ambiguities
Overage handling is stated inconsistently across the vendor's own pages: the pricing FAQ says nothing breaks, Lindy simply pauses credit-using actions until the next cycle and admins move to a larger plan, while the homepage FAQ says admins can top up at $10 per 1,000 credits or set per-person spend caps. Whether ad-hoc top-ups exist is therefore unresolved. Enterprise is custom with no public figure. The legacy phone-agent pricing carried on the old record, $10 per phone number per month with voice minutes billed in credits, is not on any current pricing surface and may have gone with the classic builder. Model coverage is described as all models in the feature list and most major models in the usage section.
Cancellation / refund
Plus can cancel anytime; no long-term contract on Plus; refund policy not public in captured pages
Support SLA / resale
Help center/community on Plus; dedicated support, onboarding, SCIM/SSO on Enterprise
Related vendors
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agent.ai — A marketplace and network of hundreds of prebuilt AI agents plus a…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No-code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
- Airia — Enterprise platform that unifies agent orchestration, security, and…
Alternatives to Lindy
The closest documented capability profiles to Lindy among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Cassidy9.5 / 14Fuller documented coverage on APIs, SDKs & MCP ExtensibilityLindy vs Cassidy →
- Gumloop13.5 / 14Adds documented Deployment & Data Residency and Testing, Debugging & OptimizationLindy vs Gumloop →
- Relay.app9.5 / 14Adds documented Testing, Debugging & Optimization
- Taskade9.5 / 14Fuller documented coverage on APIs, SDKs & MCP ExtensibilityLindy vs Taskade →
- Kalcend10.0 / 14Adds documented Testing, Debugging & Optimization
- Latenode13.0 / 14Adds documented Deployment & Data Residency and Testing, Debugging & Optimization
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded