Ambient AI · captures, indexes, surfaces, remembers

Watches. Indexes. Surfaces.
A quiet memory for every AI on your Mac.

Beside captures what you do on your computer, indexes it into a self-organising knowledge base, quietly surfaces what matters, and remembers it as long-term context for every AI agent you use — securely on-device.

100% local-first Free during beta Works with MCP
Live pipeline

It captures, indexes, surfaces — and remembers.

Four quiet loops, running in the background of your machine. Together they turn every signal on your computer into structured memory your AI agents can actually use.

1Capture

Watches every app, quietly.

Screenshots, active window, URLs, idle state — appended locally with negligible overhead.

2Index

Shapes raw signals into knowledge.

A local model extracts entities and topics, then continuously refactors the wiki.

3Surface

Pins the moments that matter.

Patterns, follow-ups, half-finished threads — Beside surfaces them when you'll need them.

4Recall

Remembers it — for every AI you use.

Claude, Cursor, ChatGPT — any MCP agent — gets persistent context, on demand.

What it does

An always-on context layer, tuned for the AI age.

LLMs forget. Agents start from zero. Beside is the quiet layer in between — continuously turning what you actually do on your computer into recallable memory that any tool can use.

01

Silent capture

Screenshots, active window, URLs, idle state — captured locally with negligible overhead. Nothing leaves your machine unless you say so.

02

Self-organising knowledge

A local model turns captures into structured notes, topics, and timelines. The wiki re-organises itself as your work evolves.

03

Proactive surfacing

Beside watches for the moments that matter — patterns, follow-ups, half-finished threads — and quietly pins them where you'll see them.

04

Memory for agents

Ship rich context to Claude, ChatGPT, Cursor and any MCP-compatible agent — so they remember yesterday, last week, last quarter.

05

Local-first by design

Raw data lives as JSONL + SQLite on your disk. Bring your own model — Ollama, OpenAI, Anthropic — or run fully offline.

06

OCR & semantic search

Every screenshot is OCR'd and embedded so you can search across everything you've ever seen — in plain English.

Under the hood

From captured pixels to living memory.

The same four loops, in technical detail. Each stage is a swappable plugin — capture, storage, model, index, export.

  1. 1

    Capture

    The capture layer records screenshots, focused windows, URLs and idle events — running silently in the background with negligible overhead.

  2. 2

    Store

    Raw events are appended to immutable JSONL + SQLite locally. Nothing is destructive; everything is replayable.

  3. 3

    Index & surface

    A local LLM extracts entities, topics, and intents, continuously refactors the wiki, and surfaces patterns worth your attention.

  4. 4

    Recall

    Expose your memory to any AI agent over MCP, Markdown, or a simple API. Context engineering, finally automated.

Free during beta

Give your AI a memory worth keeping.

Install Beside once and every AI tool you use gets quietly smarter about you.

Windows & Linux — coming soon.