> For the complete documentation index, see [llms.txt](https://www.conserver.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.conserver.io/conserver/conserver-introduction.md). # Conserver Introduction Explains what a conserver is for and why conversations need their own processing server, with the public sources behind each claim. A conserver is the server that receives vCons after a conversation ends, processes them, and delivers the results to the systems that use them. An adapter on a phone system, contact center queue or chat platform turns each conversation into a vCon and posts it to the conserver. The conserver runs it through a configured chain of links (transcription, redaction, summarization, tagging, routing, ledger registration) and writes the finished record to databases, object stores, search indexes or the [vCon MCP server](/mcp-server.md). The reference implementation is open source under the MIT license at [vcon-dev/vcon-server](https://github.com/vcon-dev/vcon-server).
Conversation sources feed the conserver, which extracts, transforms and serves vCons to business systems

Sources on the left, business systems on the right, the conserver extracting, transforming and serving vCons in between

## Why conversations need their own server A recorded conversation is a large media file plus who spoke, when, under what consent, and what every later process derived from it. A conserver keeps all of that in one vCon and adds to it at each step, so the transcript, the summary and the consent record stay attached to the call they describe. The vCon carries its own [lawful basis](/extensions/lawful-basis.md) and its [lifecycle](/extensions/lifecycle.md) events, which is what lets a deletion request or a consent withdrawal be answered from the record itself. Industry commentary makes the same point. CRM analyst Thomas Wieberneit, in [The vCon Reality Check](http://blog.aheadcrm.co.nz/2026/04/the-vcon-reality-check-moving-beyond.html), argues for putting conversational data infrastructure ahead of AI marketing, and notes that a vCon makes it possible to pinpoint the container holding an interaction, "providing an auditable trail for consent and compliance." Steve Lasker's TADSummit 2024 keynote ([session page](https://blog.tadsummit.com/2024/10/29/the-rise-and-rise-of-vcon/)) makes the case that combining SCITT and vCon delivers AI governance for conversations at scale. The conserver's `scitt` link and storage are where that happens. ## Public vCon deployments The [vCon Progress Report (TADSummit, August 2025)](https://blog.tadsummit.com/2025/08/20/vcon-progress-report/) describes a company serving car dealerships and a contact center company working together to embed vCons in the contact center, and a pilot with 211 social services contact centers across the U.S. For more public material see [Talks, Articles and Press](/talks-articles-press.md). ## Related pages * [Concepts](/conserver/concepts.md) defines links, chains, storages and tracers, and how a chain runs. * [Quick Start](/conserver/conserver-quick-start.md) gets one running. * [Operational Benefits](/conserver/operational-benefits-of-conservers.md) covers what running one buys you. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.conserver.io/conserver/conserver-introduction.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.