# Lindy — AI Agents & Assistants

Lindy by Lindy holds a panel rating of 2.5/5 from 6 AI judges (category median 2.5/5), as of 2026-11-04. Provenance: provenance unknown; sovereignty: 2 of 6 dimensions proven.

- Vendor: Lindy (https://www.lindy.ai)
- Category: [AI Agents & Assistants](https://whats-best.ai/software/ai-agents.md)
- Provenance (editorial classification): provenance unknown
- Canonical page: https://whats-best.ai/software/ai-agents/lindy
- Alternatives: https://whats-best.ai/software/ai-agents/lindy/alternatives ([markdown](https://whats-best.ai/software/ai-agents/lindy/alternatives.md))
- Data as of: 2026-11-04 · evaluated 2026-11-04 · oldest source captured 2026-11-03

**AI-generated.** Every score, rationale and verdict here is written by a panel of AI judges from public evidence — an analysis, not a hands-on test. Every fact quotes the vendor page it was read from. No score can be bought. How scores are made: https://whats-best.ai/methodology

## At a glance

- Vendor: Lindy
- Headquarters: Incorporated in United States [S2]
- Data hosting: Outside the EU by default; pages mention United States [S4]
- Free plan: Not stated on the vendor’s pages as of 3 Nov 2026

## The panel's verdict

Lindy is a no-code AI agent platform whose strongest categories are administration and access, where scores cluster at 6, and integrations and knowledge at 6-7, built on a library of 1,500+ apps and MCP support that auto-creates actions from the tools a hosted server publishes. Agent capabilities score 5-7; the customer-service director sits at 5, citing no public information on test and evaluation tooling before go-live or documented failure handling. Pricing transparency is the weakest category, spread from 1 to 3 — the skeptic finds no public prices beyond $50 in free credits with no credit card required, while higher scores credit the terms' description of subscription, per-user or usage-based billing. Processing and models and sovereignty both cluster at 4: the terms state the services are hosted in the United States under Crivello Corp, the security page says residency requirements are supported, and the judges found no public information on EU hosting or EU inference. Data use and training scores 4-6 on a written no-training commitment with thin retention detail. Persona-weighted totals fall between 4.6 and 5.6.

**Speaks for it:**
- The terms commit in writing that neither Lindy nor its model providers train on customer contributions, with a DPA and standard contractual clauses offered.
- Enterprise single sign-on and SCIM provisioning run through WorkOS, and every agent action is logged with visibility.
- MCP support auto-creates actions from any hosted server's published tools, on top of 1,500+ apps including Gmail, Slack, Notion and HubSpot.
- Agents run multi-step tasks without code on schedules and triggers, under user-set revocable permissions with approvals built in.
- Subprocessors are named with their locations — Anthropic, AWS, Google Cloud, Deepgram and WorkOS among them.

**Held against it:**
- Pricing transparency scores 1-3 — we found no public per-seat, per-tier or usage rate; the only public figures are $50 in free credits and no credit card required.
- Retention is stated only as keeping data as long as necessary, and we found no public information on admin-configurable retention or chat-deletion controls.
- The terms state the services are hosted in the United States, and we found no public information on an EU processing option, provider exclusion or bring-your-own-key.
- We found no public information on test or evaluation tooling before release, agent versioning or per-agent cost monitoring.
- We found no public information on exportable audit logs, group-level permissions over models and connectors, or documented usage analytics.

**Best for:**
- You need no-code agents handling routine multi-step work across a wide stack, with built-in approvals and a log of every action before consequential steps.
- Your compliance review hinges on a written no-training commitment covering vendor and model providers, standard contractual clauses, and a SOC 2 Type 2 report available on request.
- You accept SCC-based transfers over a documented United States stack in exchange for subprocessor transparency that names every provider and its location.
- You want to pilot before committing spend, starting with $50 in free credits and no credit card required.

**Avoid if:**
- Your deployment requires EU hosting, an EU contracting entity or EU inference — the terms state the services are hosted in the United States, and the judges report every disclosed provider and hosting region as United States or global.
- You must forecast annual spend from public prices — the captured pages publish no per-seat or per-tier figure, and the terms state purchases are non-refundable with prices changeable at any time.
- You need documented retention control — the privacy statement keeps personal information only as long as necessary, and we found no public information on admin-configurable retention periods or chat-deletion controls.

## Scores by judge and criterion

Scores out of 5, each judge scoring independently against the published rubric (v1). "n/r" = not rated: the vendor publishes no price, or the judge found no public information on that criterion.

| Criterion | The Head of IT | The Data Protection Officer | The Automation Lead | The Customer-Service Director | The Works Council Member | The Skeptic |
| --- | --- | --- | --- | --- | --- | --- |
| Data use, training & retention | 3/5 | 3/5 | 3/5 | 2.5/5 | 2/5 | 2.5/5 |
| Models & processing location | 2/5 | 2/5 | 2/5 | 2/5 | 2/5 | 2/5 |
| Admin, identity & access controls | 3/5 | 3/5 | 3/5 | 3/5 | 3/5 | 3/5 |
| Integrations, connectors & knowledge | 3/5 | 3/5 | 3.5/5 | 3/5 | 3/5 | 3/5 |
| Agent capabilities & guardrails | 3.5/5 | 3.5/5 | 3.5/5 | 2.5/5 | 3.5/5 | 3/5 |
| European sovereignty | 2/5 | 2/5 | 2/5 | 2/5 | 2/5 | 2/5 |
| Pricing transparency | 1.5/5 | 1.5/5 | 1/5 | 1.5/5 | 1/5 | 0.5/5 |
| **Weighted verdict** | **2.5/5** | **2.5/5** | **3/5** | **2.5/5** | **2.5/5** | **2.5/5** |

### The judges

- **The Head of IT** (v1.0): Has to roll an AI assistant out to eight hundred staff without a second shadow-IT wave. Wants SSO and SCIM, groups that decide who gets which model, agent and connector, answers that respect SharePoint permissions, audit logs for the SIEM, and a deployment option that is not "trust us".
- **The Data Protection Officer** (v1.0): Signs the DPA and gets asked where a prompt goes. Wants every model provider named as a subprocessor with its region, training excluded for all of them, retention the company controls, and an EU-only switch that also covers agents and connectors — not just the chat window.
- **The Automation Lead** (v1.0): Builds the agents that file tickets, draft offers and chase approvals across the ERP, CRM and wiki. Wants tools and actions with scoped permissions, MCP and an API, approval steps before anything is sent, run logs, and a way to test an agent before the whole company uses it.
- **The Customer-Service Director** (v1.0): Runs a contact centre with forty agents and wants half the routine calls and chats answered by an AI agent. Wants handover to a human with the full context, actions in the order and ticket systems, evaluation before go-live, and a price per conversation the CFO can forecast.
- **The Works Council Member** (v1.0): Has a co-determination right the moment a tool can monitor staff, and an AI assistant logs every prompt. Wants usage reports that can be aggregated or pseudonymised, prompt logging rules set out in writing, a human approving what agents do to colleagues, and no training on staff input.
- **The Skeptic** (v1.0): Has read "European AI" on a wrapper that sends every prompt to a US model, "agents" that are saved prompts, and "we never train on your data" with no word on the model provider behind it. Asks which model answers, where it runs, what it may do unsupervised, and what a thousand seats cost.

## European sovereignty — proven facts

Built only from facts on the vendor's own pages; a dimension we could not prove is left open, never scored as zero. Headline: 2 of 6 dimensions proven.

| Dimension | Finding | Points | Source |
|---|---|---|---|
| Legal entity | Incorporated in US | 0/2 | [S2] |
| Hosting location | Outside the EU | 0/4 | [S4] |
| Hosting options | Not determined | — | — |
| Open source | Not determined | — | — |
| Data processing agreement | Not determined | — | — |
| Transfer impact assessment | Not determined | — | — |

## Key facts

Each fact is the vendor's own statement, cited to the source page it was read from ([S*n*] → Sources).

**Compliance**
- AI training: yes · no [S2]
- Certifications: HIPAA · PIPEDA · SOC 2 Type 2 [S4]
- Certifications: Compliant · GDPR · SOC 2 · HIPAA · PIPEDA [S3]
- Certifications: yes · yes · yes · yes [S8]
- Data privacy posture: systems designed for data privacy/security; severely limited access to user data [S4]
- Data residency: yes · yes [S6]
- Data training: yes · yes [S6]
- Dnt: no [S3]
- Eea UK rights: yes [S3]
- Encryption: yes · yes [S4]
- Encryption: yes · yes [S6]
- GDPR: yes [S5]
- GDPR: yes [S6]
- GDPR: yes [S7]
- GDPR processor terms: processor for customers as controllers · yes · yes [S2]
- Google API training: no · no [S3]
- HIPAA: yes [S5]
- HIPAA: yes [S6]
- HIPAA: yes [S7]
- HIPAA not compliant: yes · no · yes [S2]
- Minors: 18 · no [S3]
- Pipeda: yes [S5]
- Pipeda: yes [S6]
- Pipeda: yes [S7]
- Privacy contact: privacy@lindy.ai [S3]
- Scc transfers: One · Two · yes [S2]
- Sensitive data: Health data, with consent or as permitted by law [S3]
- SOC 2: yes [S5]
- SOC 2: Type II · Johanson Group · yes [S6]
- SOC 2: yes [S7]
- SOC 2 type2: yes [S4]
- Stripe payments: Stripe [S3]

**Data**
- Collection personal: name, email, contact preferences, contact/auth data, billing addresses [S3]
- Deletion: yes [S3]
- Opt out timeline: 15 [S3]
- Retention: retained only as long as necessary unless law requires longer; no longer than account lifetime [S3]
- Sale: no [S3]
- Third party reception: no [S3]

**Hosting**
- Infrastructure: Enterprise-grade cloud infrastructure, tenant-isolated [S6]
- Region: United States [S2]

**Integrations**
- App count: 1500 · yes [S5]
- App count: 1500 · yes [S7]
- App count: yes · 1500 [S8]
- Builtin plus mcp: Built-in integrations plus MCP for any product publishing an MCP server [S9]
- Connected apps: Connects third-party accounts and apps such as email, calendar, Slack, CRM so the Services can read and act on data on your behalf [S2]
- Count: 1500 · Gmail · Slack · Notion · HubSpot · yes [S1]
- Slack delivery: yes [S7]

**Legal**
- Address: Crivello Corp · 9450 SW Gemini Dr, PMB 43040, Beaverton, OR 97008, United States [S3]
- Copyright: © 2026 Lindy [S8]
- Entity: Lindy · Crivello Corp · 9450 SW Gemini Dr, Beaverton, OR 97008 · Oregon, United States [S2]
- Entity: Lindy · Crivello Corp [S3]
- Identity disclaimer: Not associated with Lindy Electronik Gmbh [S8]
- Minimum age: 18 [S2]
- Not associated: Lindy is not associated with Lindy Electronik Gmbh [S3]
- Not lindy electronik: Not associated with Lindy Electronik Gmbh [S6]
- Terms last updated: 2026-09-24 [S2]

**Pricing**
- Currency: USD · yes · yes [S2]
- Free credits: 50 · no [S5]
- Free credits: 50 [S7]
- Free credits: 50 [S8]
- No credit card: no [S7]
- No credit card: no [S8]
- Overages: yes · yes [S2]
- Payment methods: Visa · Mastercard · American Express · Discover · PayPal [S2]
- Refund policy: no · end of current paid term · yes [S2]
- Workspace billing model: subscription fees, charges based on users or usage, or a combination · yes [S2]
- Workspace trials: yes · yes [S2]

**Product**
- Access control: Least-privilege access control with built-in approvals [S6]
- Analyze sentiment: Analyze Sentiment: determine sentiment or emotional tone of content [S5]
- Audit logging: All Lindy actions logged with visibility [S6]
- Channels: web app, Chrome extension, integrations such as Slack, iMessage, email, meeting joining [S3]
- Cross app tasks: yes [S7]
- Extract keywords: Extract Keywords: extract keywords and key phrases from text [S5]
- Generate blog post: Generate Blog Post from provided text [S5]
- Generate headline: Generate Headline from text using AI models [S5]
- Generate text: Generate Text using AI models [S5]
- Gworkspace admin actions: 4 [S7]
- Lindy phone: phone calling and messaging functionality · yes [S2]
- List activities by admin: Retrieve activities performed by a Google Workspace admin user for a specific application. [S7]
- List activities by event name: Retrieve Google Workspace activities filtered by event name and application. [S7]
- List activities by event name and admin: List activities for a specific Google Workspace event and administrator. [S7]
- List all activities: Retrieve activity logs for specified Google Workspace applications within a given timeframe. [S7]
- Mcp auth options: Supports anonymous access, server-side OAuth, or static credential as bearer token, custom header, or query parameter [S9]
- Mcp auto action creation: Auto-creates actions for every supported tool schema; no action-picking or field-mapping step [S9]
- Mcp capabilities: Read/act on MCP server data and trigger workflows on changes [S8]
- Mcp endpoint requirement: Requires a public HTTPS streamable-HTTP endpoint [S9]
- Mcp hosted server support: Lindy connects to hosted MCP servers and auto-builds actions from published tools [S9]
- Mcp support: Supports connecting any MCP server, used via plain language in Slack, no workflows to build [S8]
- Mcp workspace admin permissions: Workspace owners/admins can revoke sharing and set policy but cannot grant sharing or reconnect credentials [S9]
- Meetings: yes · yes [S1]
- Meetings recordings: yes · yes · yes · yes [S2]
- Mention activation: Activated by @mentioning Lindy in any Slack channel [S8]
- Metatext actions count: 6 [S5]
- Mission: no-code platform for AI/LLM agents [S4]
- No code natural language: no [S7]
- Recurring routines: yes [S5]
- Routines: Supports scheduled recurring routines [S8]
- Routines scheduling: yes [S7]
- Slack integration: Installs via Slack marketplace with one click; whole team gets access [S8]
- Slack trigger: yes [S5]
- Spam or not: Spam Or Not: detect spam vs legitimate text [S5]
- Triggers on changes: yes · yes [S7]
- User permissions: User-set, revocable permissions [S6]

**Subprocessors**
- Agent infra: Agent Infrastructure · Temporal · E2B · Superserve · Mesa · GitHub [S3]
- AI models: AI Model & AI Service Providers · Anthropic · OpenAI · Perplexity AI · Exa Labs · ElevenLabs · Deepgram [S3]
- Analytics: Data Analytics & Monitoring · PostHog · Datadog · Honeycomb · Sentry · Snowflake · Fivetran · Omni [S3]
- Anthropic: Anthropic · AI inference and AI services (Claude LLM) · USA [S4]
- Aws: Amazon Web Services · Object storage (S3) · United States [S4]
- Baseten: Baseten · AI model inference (MAPI) · Global / multiple regions · yes [S4]
- Cloud: Cloud Computing & Storage · Google Cloud Platform · Amazon Web Services · DigitalOcean · MongoDB · Cloudflare [S3]
- Communications: Communication Tools · Twilio (including SendGrid) · LINQ · Infobip · Recall.ai [S3]
- Deepgram: Deepgram, Inc. · Speech-to-text and audio transcription · United States [S4]
- E2b: E2B Dev, Inc. · Code execution sandbox (Computer Use) · United States [S4]
- Gcp: Google Cloud Platform · Cloud Infrastructure and Security · USA [S4]
- Hosting: Website Hosting Service Providers · Webflow [S3]
- Integrations auth: Integrations & Authentication · Pipedream · WorkOS [S3]
- Payments: Payment Processing & Billing · Stripe · Orb [S3]
- Recall: Recall.ai, Inc. · Meeting bot and recording services · United States [S4]
- Stripe: Stripe · Payment processing platform · USA [S4]
- Temporal: Temporal Technologies, Inc. · Workflow orchestration (Temporal Cloud) · United States [S4]
- Workos: WorkOS, Inc. · Enterprise single sign-on (SSO) and directory synchronization (SCIM) · United States [S4]

**Support**
- Security contact: security team contact [S6]
- SOC 2 reports: yes · yes [S6]
- Trust center access: yes · yes · yes [S4]

## Questions

### Is Lindy European?

Not determined: the vendor’s pages as captured do not say where Lindy is based. Its vendor, Lindy, is incorporated in United States, per [the vendor’s page captured 3 Nov 2026](https://whats-best.ai/evidence/16819).

### Where does Lindy store data?

Lindy stores customer data outside the EU by default, per [the vendor’s page captured 3 Nov 2026](https://whats-best.ai/evidence/16821). The vendor’s pages mention United States as hosting location, per [the vendor’s page captured 3 Nov 2026](https://whats-best.ai/evidence/16819).

### Does Lindy have a free plan?

Not stated on the vendor’s pages as of 3 Nov 2026.

### What are the best alternatives to Lindy?

As of 3 Nov 2026, the panel rates [Langdock (4/5)](https://whats-best.ai/software/ai-agents/langdock), [Dust (3.5/5)](https://whats-best.ai/software/ai-agents/dust) and [Unique AI (3.5/5)](https://whats-best.ai/software/ai-agents/unique-ai) highest among the other 18 AI Agents & Assistants products evaluated. Ratings that look equal are rounded to half stars; the order uses the unrounded rating, then the name. The highest-rated European alternative is [Langdock](https://whats-best.ai/software/ai-agents/langdock) (EU-Made). Ratings are the AI panel’s opinion, formed from public evidence: [how scores are made](https://whats-best.ai/methodology#ordering). The full list, with European products first: [Lindy alternatives](https://whats-best.ai/software/ai-agents/lindy/alternatives).

## What this page leaves out

- 16 product facts could not be confirmed on the vendor’s page as captured and were left out of this page and of the panel’s material.
- 9 pricing facts could not be confirmed on the vendor’s page as captured and were left out of this page and of the panel’s material.
- 5 compliance facts could not be confirmed on the vendor’s page as captured and were left out of this page and of the panel’s material.
- 2 integrations facts could not be confirmed on the vendor’s page as captured and were left out of this page and of the panel’s material.
- 2 legal facts could not be confirmed on the vendor’s page as captured and were left out of this page and of the panel’s material.
- 1 subprocessors fact could not be confirmed on the vendor’s page as captured and was left out of this page and of the panel’s material.
- 1 support fact could not be confirmed on the vendor’s page as captured and was left out of this page and of the panel’s material.

## Sources

- [S1] Vendor page: https://www.lindy.ai (checked 2026-11-03)
- [S2] Terms of service — found from the homepage: https://www.lindy.ai/terms-of-service (checked 2026-11-03)
- [S3] Privacy policy — found from the homepage: https://www.lindy.ai/privacy (checked 2026-11-03)
- [S4] Security / trust page — found from the homepage: https://trust.lindy.ai/ (checked 2026-11-03)
- [S5] Models & processing location — found from sitemap: https://www.lindy.ai/integrations/metatext-ai-pre-build-ai-models-api (checked 2026-11-03)
- [S6] Admin, identity & access controls — found from sitemap: https://www.lindy.ai/security (checked 2026-11-03)
- [S7] Admin, identity & access controls — found from sitemap: https://www.lindy.ai/integrations/google-workspace-admin (checked 2026-11-03)
- [S8] Integrations, connectors & knowledge — found from sitemap: https://www.lindy.ai/integrations/mcp (checked 2026-11-03)
- [S9] Integrations, connectors & knowledge — found from sitemap: https://docs.lindy.ai/integrations/mcp (checked 2026-11-03)

---

Cite as: whats-best.ai, "Lindy — AI Agents & Assistants", AI panel analysis, as of 2026-11-04. https://whats-best.ai/software/ai-agents/lindy

Corrections: https://whats-best.ai/correct/1365?target=page