LlamaIndex
LlamaIndex builds document parsing and extraction software plus open-source tools for AI applications, helping teams turn enterprise documents into usable data for AI agents and workflows.

Lindy is an AI teammate for teams that want recurring work handled across the tools they already use. It connects to Gmail, Slack, Notion, HubSpot, and more than 1,500 other services, then takes on tasks like pulling reports, updating a CRM, or clearing an inbox. The pitch is straightforward: hand Lindy the work you would give a colleague, and it comes back with the work done.
Lindy is designed to work inside the software a team already relies on rather than beside it. It supports MCP, so hosted servers can plug in, and for tools without a native integration, it can drive a browser like a person would on Pro and Max plans. Setup is measured in minutes, with no API keys or IT tickets. An admin installs Lindy in Slack, everyone else links with one tap, and anyone can mention it in a channel where it has been added.
One person can take a call and the right people get the context afterward. Lindy records meetings and organizes them into a shared library with folders for teams like marketing, sales, and user research. Recordings are searchable, so questions about what customers said on a call can be answered from the relevant source. Meeting scheduling, prep, and follow-up are included as well.
Anything a team does on repeat can be handed to Lindy on a schedule: a morning brief, a Monday report, a Friday nudge. Lindy ships with more than 40 skills covering research, data analysis, slide decks, and dashboards. When someone shows Lindy how to do something once, it can be saved as a skill for the whole team. Skills and memory live in plain files, so anyone can open the memory folder, read what Lindy remembers, and edit it like a document.
Lindy is positioned as more than a chatbot. Ask why ad spend doubled and it can pull 14 days of spend from Meta and Google, join it to PostHog, and produce a teardown document with a recommendation. Ask what customers said about pricing and it answers from every relevant call. Ask for an all-hands deck and it returns slides ready to present. Other examples include triaging a support queue, turning a week of calls into a proposal, and building HTML dashboards from CRM and analytics data.
Actions with outside impact wait for approval, such as sending an email, updating a ticket, posting to another channel, or publishing a doc. Read-only lookups from approved sources do not require approval. Direct messages with Lindy stay private, and shared channels only use public sources. Lindy states that data is never sold or used to train models, and that it is encrypted in transit and at rest. The company reports SOC 2 Type II, GDPR, HIPAA, and PIPEDA compliance, with Enterprise adding SSO, audit logs, and HIPAA under a signed BAA.
Credits measure the work Lindy does, and bigger jobs use more. Everyday asks like answers, summaries, and lookups run 2 to 250 credits. Deep work such as competitor research or support triage runs 250 to 1,000. Big builds like complex dashboards and internal tools run 1,000 to 2,500. Every seat adds its credits to one shared pool, and admins can set per-person spend caps. If the pool runs low, Lindy pauses and says so rather than generating a surprise bill. Monthly credits refresh each billing cycle and do not roll over, while top-up credits remain until used.
Lindy suits teams that want an AI design co-pilot for operational work rather than another standalone chat window. The shared memory and skill library mean what one person teaches Lindy compounds for everyone. The trade-offs are the credit model, which requires some planning, and the fact that every active user takes a billed seat. Teams that live in Slack and want recurring work handled without adding another tool to the stack are the clearest fit.
Free plan includes $50 in credits, no credit card required, and credits last 7 days. Team plan starts at $49.99 per user per month for 5,000 credits each, with all seats drawing from a shared pool. Top-ups cost $10 per 1,000 credits. Enterprise pricing is custom. Monthly credits do not roll over; top-up credits do not expire.
Features, pricing and availability may change. Always verify details on the official website. Maintained by steven · Last updated Oct 16, 2026 →
LlamaIndex builds document parsing and extraction software plus open-source tools for AI applications, helping teams turn enterprise documents into usable data for AI agents and workflows.
Flowith is an agentic AI workspace that combines a whiteboard-style canvas, access to 40+ image and video models, and mini apps for design, e-commerce, and social content.
Fine-tune open models faster with far less memory
Groq is an AI inference cloud for developers and enterprises that need low-latency model responses at scale, delivered through custom LPU hardware and a tiered platform spanning bare metal, inference, and enterprise controls.