# Clanker Support > An AI-powered support agent you embed with one script tag — it answers from your docs and sources, then escalates to your team. Open and self-hostable (bring your own keys); the hosted version has flat monthly plans from $19/mo with no per-seat fees. ## Product - [Overview](https://clankersupport.com/): What Clanker Support is and how the drop-in agent works. - [Docs](https://clankersupport.com/docs): Quickstart, training on your docs, escalation, and migration. - [Compare](https://clankersupport.com/compare): How Clanker Support compares to other AI support tools. - [Pricing](https://clankersupport.com/pricing.md): Self-host (free) and hosted plans — Starter, Growth, and Scale. ## Free tools - [AI support savings calculator](https://clankersupport.com/tools/support-roi-calculator): See how many hours and dollars AI support would save your team each month. - [CSAT calculator](https://clankersupport.com/tools/csat-calculator): Turn survey responses into a CSAT score and see how you rank against benchmarks. - [Canned response generator](https://clankersupport.com/tools/canned-response-generator): Build polished, personal support replies for refunds, bugs, outages, and more. - [llms.txt generator](https://clankersupport.com/tools/llms-txt-generator): Generate a spec-correct llms.txt so AI assistants can navigate your site. ## Comparisons - [Clanker Support vs Chatbase](https://clankersupport.com/vs/chatbase): Clanker Support is a single script tag that goes live in minutes and lets you swap underlying AI models without touching your code. Chatbase is a full platform with stronger multi-channel support. Choose Clanker Support if you want simplicity and model flexibility. Choose Chatbase if you need WhatsApp, Slack, or Messenger support today. - [Clanker Support vs Chatwoot](https://clankersupport.com/vs/chatwoot): Both Clanker Support and Chatwoot are self-hostable. The difference is scope and stack: Chatwoot is a full multi-channel platform running on Rails + PostgreSQL; Clanker Support is a focused widget running serverless on Cloudflare's edge. Choose Chatwoot for open-source, multi-channel coverage. Choose Clanker Support for a lighter setup and model-agnostic AI. - [Clanker Support vs Crisp](https://clankersupport.com/vs/crisp): Crisp is an all-in-one support + CRM platform with flat pricing and European hosting. Clanker Support is a focused drop-in widget with model-agnostic AI and self-hosting. Choose Crisp if you need CRM features, omnichannel, or EU data residency. Choose Clanker Support if you want the simplest possible setup and model flexibility. - [Clanker Support vs Fin](https://clankersupport.com/vs/fin): Fin charges per resolved outcome and runs on proprietary AI models with deep enterprise integrations. Clanker Support uses flat monthly pricing, is model-agnostic, and is self-hostable. Choose Fin if you have high resolution volume and need deep helpdesk integrations. Choose Clanker Support if you want predictable pricing and model flexibility. - [Clanker Support vs Intercom](https://clankersupport.com/vs/intercom): Intercom is a full customer communication platform — support, sales, and marketing in one. If you need all three, it's a powerful investment. If you only need a support widget, you're paying for a lot you won't use. Clanker Support is purpose-built for support and costs significantly less. ## Migration guides - [Migrate from Chatbase to Clanker Support](https://clankersupport.com/docs/migrate/chatbase): From the Chatbase embed to a single Clanker Support script tag - [Migrate from Chatwoot to Clanker Support](https://clankersupport.com/docs/migrate/chatwoot): From a self-hosted Rails stack to serverless Clanker Support - [Migrate from Crisp to Clanker Support](https://clankersupport.com/docs/migrate/crisp): From the all-in-one Crisp platform to a focused Clanker Support widget - [Migrate from Fin to Clanker Support](https://clankersupport.com/docs/migrate/fin): From Fin (inside Intercom) to a standalone Clanker Support widget - [Migrate from Intercom to Clanker Support](https://clankersupport.com/docs/migrate/intercom): From the Intercom platform to a focused Clanker Support widget ## Journal - [Clanker Support is live — and we're on Product Hunt today](https://clankersupport.com/blog/clanker-support-is-live-on-product-hunt): Clanker Support is officially live and featured on Product Hunt. Here's what we built: an AI support agent that answers from your docs and hands off to a human the moment it can't. - [Introducing Clanker Support: AI support that actually escalates](https://clankersupport.com/blog/introducing-llmchat): Today we're launching Clanker Support — a drop-in widget that answers from your docs and hands off to your team when the bot can't help. - [Changelog: June 2026 — launch month](https://clankersupport.com/blog/llmchat-changelog-june-2026): We launched on Product Hunt. Also: smarter escalation, a full dashboard restyle, workspace-wide search, annual plans, and a security hardening pass. - [Changelog: May 2026 — knowledge base improvements and new model options](https://clankersupport.com/blog/llmchat-changelog-may-2026): Longer knowledge base support, model selection per project, and a handful of inbox quality-of-life improvements. - [How to reduce support tickets by 60% with an AI first-response layer](https://clankersupport.com/blog/reducing-support-tickets-with-ai-first-response): A practical guide to deploying an AI first-responder that handles the repetitive stuff so your team can focus on the conversations that matter. - [Setting up email threading for your support widget](https://clankersupport.com/blog/setting-up-email-threading): A step-by-step guide to configuring inbound email so customer replies thread back into the same conversation. - [The case for self-hostable AI support](https://clankersupport.com/blog/the-case-for-self-hostable-ai-support): Why open architecture matters for tools that sit between you and your customers. - [Why we built on LLM Gateway instead of calling OpenAI directly](https://clankersupport.com/blog/why-we-built-on-llm-gateway): Our reasoning for using a model abstraction layer from day one — and why it's already paid off twice.