---
title: "Pace vs Impulse"
description: "An evidence-based comparison of Pace and Impulse: conversation-wide memory vs per-project SwiftData."
canonical: https://heypace.app/compared/impulse/
last-updated: 2026-08-27
---
# Pace vs Impulse

An evidence-based comparison of Pace and Impulse: conversation-wide memory vs per-project SwiftData.

## Product posture

- **Product:** [Impulse](https://github.com/section9-lab/Impulse)
- **Maintainer:** section9-lab
- **License:** Apache-2.0; open source under Apache-2.0
- **Runtime posture:** hybrid
- **Speech-to-text:** Speech framework (on-device)
- **Reasoner:** Any OpenAI-compatible / Ollama / LM Studio
- **Text-to-speech:** Local
- **Screen-aware:** Yes

## What the competing product does well

- Per-project SwiftData memory — conversations scoped to the project you're working in.
- JSONL session logs that are diffable and greppable.
- Vision framework OCR on-device; security-scoped bookmarks for sandboxed file access.
- Tool calls are visible in chat before they run.

## Where Pace differs

Pace's memory is conversation-wide two-tier (verbatim K=4 + rolling summary) with cross-quit persistence. Impulse's is per-project SwiftData. Pace adds actions, MCP, and a tier picker; Impulse is more focused on project-scoped chat.

This comparison does not claim ratings, market rank, or user-review scores.