> 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.md).

# Conserver

Start here to learn what the conserver does, get one running, configure it, and find the reference page for each part.

The conserver is an open source server that takes in vCons, runs each one through a configured chain of processing steps, and writes the result to the storage systems you choose. Steps are called links: transcribe, summarize, tag, route, redact, notify, register on a SCITT ledger. The current build ships 23 links and 15 storage modules. Source: [vcon-dev/vcon-server](https://github.com/vcon-dev/vcon-server) (MIT, Python 3.12, FastAPI, Redis, Docker Compose).

Use a conserver when vCons arrive from adapters (phone systems, SIPREC, chat, AI agent sessions) and something has to happen to every one of them, the same way, with failures captured in dead letter queues.

## Path through this section

**1. Understand it**

* [Conserver Introduction](/conserver/conserver-introduction.md): what a conserver is for, with public sources
* [Concepts](/conserver/concepts.md): vCon, link, chain, ingress and egress lists, storage, dead letter queues, tracer, follower. The rules for how a chain runs live here.
* [Day in the Life of a vCon](/conserver/day-in-the-life-of-a-vcon.md): one phone call followed from adapter to AI assistant
* [The Journey of a vCon](/vcons/vcon-conveyor-infographic.md): the same trip as an interactive picture

**2. Run it**

* [Quick Start](/conserver/conserver-quick-start.md): a working conserver on Docker Compose

**3. Configure it**

* [Configuring the Conserver](/conserver/configuring-the-conserver.md): environment variables and every `config.yml` section
* [Standard Links](/conserver/standard-links.md): all 23 links and their options
* [Storage](/conserver/storage.md): all 15 storage modules
* [Conserver Tracers](/conserver/conserver-tracers.md): the JLINC audit tracer

**4. Build on it**

* [Integrating Your App](/conserver/integrating-your-app.md): sending vCons in and reading results out
* [API](/conserver/api.md): every REST endpoint
* [Creating Custom Links](/conserver/creating-custom-links.md): writing your own processing step

**5. Operate it**

* [Production Deployment](/conserver/production-deployment.md): scaling, secrets, observability
* [Inside the Conserver](/conserver/inside-the-conserver.md): workers, Redis keys and the processing loop
* [Troubleshooting](/conserver/troubleshooting.md): common failures and fixes
* [Operational Benefits](/conserver/operational-benefits-of-conservers.md): what running one buys you, with public sources


---

# 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.md?ask=<question>&goal=<user_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.