> ## Documentation Index
> Fetch the complete documentation index at: https://nemonist.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# What is nemonist

> A drop-in endpoint for the models you already use, with a memory for each workspace that learns from every turn.

nemonist keeps a memory for each workspace and learns from every turn. Correct your agent once and it changes how it works; decisions, conventions and unfinished work carry over to every new chat, client and model.

It is a drop-in endpoint: point your client at nemonist and keep your tools, models and habits. No plugin, no SDK.

> [card] [Quickstart](https://nemonist.com/docs/quickstart.md)
>
> A key, one request, then your client. About a minute.

> [card] [Connect your client](https://nemonist.com/docs/clients/cursor.md)
>
> Cursor, Claude Code, Codex, OpenCode and the OpenAI SDKs.

> [card] [How memory works](https://nemonist.com/docs/concepts/memory.md)
>
> Workspaces, the learning loop, and what you can read or erase.

> [card] [API Reference](https://nemonist.com/docs/api-reference/overview.md)
>
> Every endpoint, with a playground.

## What changes for your agent

* **Learns from every turn.** Corrections, repeated asks and wins turn into better practice. Your agent changes how it works, not only what it knows.
* **Remembers across chats.** Start a new chat and your agent already knows the decisions, preferences and gotchas from the last one.
* **Picks up unfinished work.** Open tasks carry over to the next chat, the next client and the next model, with why each one is still open.
* **One memory per workspace.** Each project learns on its own, so practice from one repo never leaks into another. Private to your account.
* **Every major model.** Hundreds of models from every major provider, behind one key, with activity, logs and limits.

## The learning loop

**1. Recall**

Before it answers, your agent reads the notes that bear on the task: conventions, past decisions, what went wrong last time.

**2. Act**

Your model answers as usual, with the same tools and the same client.

**3. Judge**

Your next message shows how that went: a correction, a repeat, an error or a success. The agent judges it and how much it matters.

**4. Improve**

It rewrites the notes that led there, so the lesson sticks and the next turn, in any chat, starts better than the last.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.