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

# Introduction

> Your AI agent's long-term memory. Remember everything. As simple as files, as powerful as Postgres.

# Your AI Agent's Long-Term Memory

Remember every conversation. Search instantly. Never repeat yourself.

Bossa gives your AI agents a persistent filesystem to store and retrieve context across sessions—just like Claude Code and Manus do.

<Callout icon="leaf" color="#16A34A">
  **Install:** `pip install bossa-memory` · **Base URL:** `https://bossamemory.com` · No infrastructure to run. Sign up, get an API key, start building.
</Callout>

**Free tier:** 100 MB storage, 1,000 requests/day. No credit card required.

[Get Started Free](/GETTING_STARTED) · [Pricing](/PRICING) · [GitHub](https://github.com/vinny380/bossa)

***

## The Problem: Agents Forget Everything

Every time your agent starts, it's like Groundhog Day:

* Re-learning user preferences every session
* Asking the same questions over and over
* No memory of previous work or context
* RAG pipelines that are complex and brittle

**Claude Code and Manus solved this with filesystems.** Now you can too.

***

## Why Filesystem Over RAG?

Leading agent platforms like Claude Code and Manus chose filesystems over traditional RAG pipelines. Here's why:

| Filesystem (Bossa)                 | Traditional RAG                |
| ---------------------------------- | ------------------------------ |
| `grep "user preferences"`          | Tune embeddings, pray it works |
| Directory structure = organization | Flat vector space              |
| Works like CLI tools agents know   | New abstractions to learn      |
| Debuggable with `ls`, `cat`        | Black box retrieval            |
| No embedding drift                 | Constant re-indexing           |

**For 80% of agent use cases, filesystems just work better.**

[Read: Why We Chose Filesystem Over RAG →](/WHY_FILESYSTEM)

***

## Why Bossa?

### Feels Like Local Files

```bash theme={"theme":{"light":"min-light","dark":"min-dark"}}
bossa files ls /memory
bossa files read /user/preferences.json
bossa files grep "project alpha"
```

Just standard filesystem operations. No new concepts.

### Powered by Postgres

* Full-text search with trigrams
* ACID transactions
* JSON storage
* Enterprise-ready

### Plug-and-Play

| Platform            | How to connect                                        |
| ------------------- | ----------------------------------------------------- |
| **Terminal**        | `export BOSSA_API_KEY=sk-xxx` then `bossa files ls /` |
| **LangChain**       | Add Bossa MCP server to `MultiServerMCPClient`        |
| **Claude / Cursor** | Add MCP server URL + API key in headers               |

One line of code. That's it.

### Your Agent's Personal File System

Each agent gets its own space, scoped by API key. No cross-tenant leakage.

***

## How Does Bossa Help Me?

<Columns cols={3}>
  <Card title="Coding Assistant" icon="code" href="/USE_CASES">
    Remember project context, tech stack, and conventions across sessions.
  </Card>

  <Card title="Multi-Agent Team" icon="users" href="/USE_CASES">
    Multiple agents share one workspace. Handoffs, shared state, no duplicate work.
  </Card>

  <Card title="Context Engineering" icon="search" href="/USE_CASES">
    Discover what's relevant with ls/grep, pull only what you need. Fewer tokens.
  </Card>
</Columns>

[See More Examples →](/USE_CASES)

***

## Quick start

<Steps>
  <Step title="Sign up">
    [Create an account](GETTING_STARTED#2-sign-up--log-in) via the CLI
  </Step>

  <Step title="Create workspace & key">
    [Create a workspace and API key](GETTING_STARTED#3-create-a-workspace--api-key)
  </Step>

  <Step title="Connect">
    [Make your first request](GETTING_STARTED#4-make-your-first-request) via MCP or REST
  </Step>
</Steps>

***

## Docs MCP

Give your AI assistant (Cursor, VS Code, Claude) direct access to the Bossa documentation. Use the contextual menu at the top of any page for **one-click Connect to Cursor** or **Connect to VS Code** — or follow the [manual setup instructions](/ADD_DOCS_AS_MCP).

[Add Docs to Your IDE →](/ADD_DOCS_AS_MCP)

***

## Documentation

<Columns cols={2}>
  <Card title="Getting Started" icon="rocket" href="/GETTING_STARTED">
    Sign up, API key, first request.
  </Card>

  <Card title="Why Filesystem?" icon="lightbulb" href="/WHY_FILESYSTEM">
    Filesystem vs RAG — why we chose this approach.
  </Card>

  <Card title="Dynamic Context Discovery" icon="search" href="/DYNAMIC_CONTEXT_DISCOVERY">
    How Bossa fits the context-engineering pattern used by Cursor and LangChain.
  </Card>

  <Card title="Docs as MCP" icon="cpu" href="/ADD_DOCS_AS_MCP">
    Add Bossa docs to Cursor, VS Code, Claude.
  </Card>

  <Card title="CLI Reference" icon="terminal" href="/CLI">
    Auth, workspaces, keys, files.
  </Card>

  <Card title="MCP Integration" icon="puzzle" href="/MCP">
    Claude, Cursor, LangChain.
  </Card>

  <Card title="REST API" icon="code" href="/REST_API">
    Endpoint reference.
  </Card>

  <Card title="Agent Integration" icon="robot" href="/AGENT_INTEGRATION">
    Examples and patterns.
  </Card>

  <Card title="Use Cases" icon="layers" href="/USE_CASES">
    Coding assistant, multi-agent team, context engineering.
  </Card>

  <Card title="Self-Hosting" icon="server" href="/SELF_HOSTING">
    Run on your infrastructure.
  </Card>
</Columns>