# Durable context — shared persistent memory for AI agents

> Shared persistent memory for AI agents. slivingdoc calls this durable context: plain-text notes that agents and people share across sessions and machines.

Canonical URL: https://www.slivingdoc.dev/docs/concepts/durable-context/ · Version: 1.0 · Updated: 2026-09-30

Full site index: https://www.slivingdoc.dev/llms.txt

Persistent memory for an AI agent is information that remains available
after its session ends. slivingdoc provides shared persistent memory in a
notebook of plain-text files stored on slivingdoc.dev or in your own
S3-compatible bucket. Agents use MCP or the CLI to pull notes and commit
changes. People can edit the same files. We call this durable context:
shared knowledge that lasts across sessions, machines, and agents. Agents
choose which notes to read and write; slivingdoc stores and shares them.

## Why AI agents need persistent memory

An agent's working context is short-lived by default:

- **The context window** is gone when the session ends or is compacted.
- **A local file** lives on one disk. CI jobs, sandboxes and scheduled
  agents lose theirs after every run, and a laptop's notes never reach
  the agent running in production.
- **One agent's memory** is not another's. Claude Code, Codex and any
  other MCP host each keep their own, and a fleet of agents cannot read
  what its siblings learned.

Context that has to be rediscovered costs tokens, time and mistakes.

## What makes context durable

slivingdoc treats context as data with three properties:

- **It outlives the session and the machine.** The notebook lives in
  hosted storage on slivingdoc.dev or in your own S3-compatible bucket.
  Once committed, everything slivingdoc keeps on a local disk can be
  thrown away and rebuilt from it. See
  [Storage model](/docs/concepts/storage-model/).
- **It is shared.** Every agent and every person pulls the same notebook
  and commits changes back. Concurrent, non-conflicting edits are merged
  with Git semantics; overlapping edits return a conflict instead of
  silently overwriting accepted work. See
  [How it works](/docs/concepts/how-it-works/).
- **It stays plain text.** Notes are ordinary UTF-8 files that agents
  read and edit with the file tools they already have, and people edit
  with any editor. There is no schema to agree on, and agents and people
  need no protocol between them.

slivingdoc keeps the current state durable; it does not promise
historical recovery and is not a backup product. See
[Guarantees and limits](/docs/concepts/guarantees/).

## Durable context in practice

- **One context for every coding agent.** A decision written in one
  session is there in the next, whichever MCP host runs it. See
  [Connect an MCP host](/docs/guides/mcp-hosts/).
- **Memory for short-lived runners.** The next CI run or scheduled agent
  starts where the last one stopped. See
  [From scripts and cron](/docs/guides/cli/#from-scripts-and-cron).
- **Instructions you change at runtime.** Keep shared instructions under
  read-only paths, edit them from the command line, and every agent reads the new
  version on its next pull. See
  [Read-only paths](/docs/guides/path-policies/#read-only-paths).
- **Context shared with people.** Colleagues pull and commit the same
  notebook from the command line. See
  [Share a directory](/docs/guides/shared-directory/).

To start, follow the [Quickstart](/docs/quickstart/).