# HeyPace

> Pace is a private Mac voice agent that listens, reads the current screen, and takes approved actions with local models by default.

Reach for Pace when you need a local-first macOS voice agent that transcribes speech, reads your screen, plans actions, and executes approved macOS actions. Voice and screen processing can stay local; update checks and user-selected providers or connectors are explicit network exceptions.
Best-fit jobs: voice-driven macOS automation, screen-aware voice assistance, on-device meeting notes and action capture, and local TTS streaming from a menu-bar voice agent.
Do not use Pace for cloud-based voice assistants, cross-platform (non-macOS) voice tools, or anything that requires sending audio or screen content to a remote server.
No CLI tool is currently available. Pace is a macOS menu-bar application: https://heypace.app/download.

<!-- Keep in sync with robots.txt and ai.txt. -->

## Public pages

- [HeyPace — private Mac voice agent that sees your screen](https://heypace.app/index.md): Pace is a private Mac voice agent that listens, reads the current screen, and takes approved actions with local models by default.
- [Mac AI agents that see your screen — 17 compared](https://heypace.app/compared.md): Compare 17 macOS AI agents by screen access, inference location, actions, approval model, license, and where Pace is honestly behind.
- [Download Pace](https://heypace.app/download.md): Download the on-device macOS voice companion and review its installation and update requirements.
- [Pace pricing](https://heypace.app/pricing.md): Pace offers a free Apple Foundation Models preview and a $29 one-time purchase. A $5 monthly Studio option is planned, not live.
- [Pace FAQ](https://heypace.app/faq.md): Answers about Pace privacy, hardware, local models, recordings, purchase terms, integrations, and action safety.
- [Pace changelog](https://heypace.app/changelog.md): A curated record of verified, user-visible Pace product outcomes.
- [Pace privacy](https://heypace.app/privacy.md): How Pace keeps voice, screen, meeting, and journal data local, plus the explicit exceptions that can use the network.
- [Pace terms](https://heypace.app/terms.md): Plain-language terms for Pace's MIT-licensed software and current one-time purchase path.
- [On-device AI assistant for Mac](https://heypace.app/on-device-ai-assistant-mac.md): Learn what an on-device AI assistant for Mac should keep local, how permissions and optional cloud paths work, and how Pace connects voice, screen context, actions, and memory.
- [Screen-aware AI assistant for Mac](https://heypace.app/screen-aware-ai-assistant-mac.md): Try a screen-aware Mac assistant with a read-only document workflow. Check permissions, local or cloud planning, answer accuracy and common failure cases.
- [Private voice assistant for Mac](https://heypace.app/private-voice-assistant-mac.md): Evaluate a private Mac voice assistant by its audio, planning, storage, permissions, and network boundaries—and see how Pace exposes local and optional external paths.
- [Mac AI assistant that can take actions](https://heypace.app/mac-ai-assistant-actions.md): See how a Mac AI assistant can take approved, typed, verifiable actions through accessibility, app integrations, Shortcuts, tools, and recoverable workflows.
- [On-device meeting notes for Mac](https://heypace.app/on-device-meeting-notes-mac.md): Learn how on-device meeting notes capture two audio tracks, transcribe and summarize locally, ground action items, and keep retention under user control.
- [How On-Device Mac Voice Assistants Control Desktop Actions Privately](https://heypace.app/on-device-mac-voice-control-privacy.md): Learn how macOS voice agents process audio, interpret screens, and execute local desktop actions entirely on-device without cloud LLMs or off-site telemetry.
- [Local vs Cloud Voice Agents for macOS: Evaluation Checklist](https://heypace.app/local-vs-cloud-voice-agents-macos-checklist.md): Evaluate local vs. cloud macOS voice agents across latency, offline capability, screen privacy, key storage, auditability, and action execution.
- [Screen-Aware Mac Assistants: Local Vision, Planning, and Approval](https://heypace.app/screen-aware-mac-assistants-vision-planning-approval.md): Discover how screen-aware macOS assistants use local vision, Accessibility tree inspection, bounded plan-act-observe loops, and approval gates to automate tasks safely.
- [Ora vs Pace — macOS voice agent comparison](https://heypace.app/compared/ora.md): Ora vs Pace for macOS: Pace adds a tier picker (Local / CLI bridge / Direct API / Apple FM) with byte-identical persona across tiers, visible-undo trust surfaces, and two-tier thread memory that survives quit/relaunch. Ora is single-tier local. Screen-aware voice agents compared, including where Pace is behind.
- [OpenFelix vs Pace — macOS voice agent comparison](https://heypace.app/compared/openfelix.md): OpenFelix vs Pace for macOS: Pace has MCP integration, a recipe library, and passive time-understanding journals (screen watch + app usage). OpenFelix leans into scheduled + proactive surfaces Pace doesn't ship yet. Screen-aware voice agents compared, including where Pace is behind.
- [ORB vs Pace — macOS voice agent comparison](https://heypace.app/compared/orb.md): ORB vs Pace for macOS: Pace uses a heavier qwen3-30b-a3b reasoner with a tier picker and trust surfaces. ORB is leaner and more single-purpose. Note: ORB has no license file yet, so it's effectively all-rights-reserved. Screen-aware voice agents compared, including where Pace is behind.
- [Impulse vs Pace — macOS voice agent comparison](https://heypace.app/compared/impulse.md): Impulse vs Pace for macOS: 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. Screen-aware voice agents compared, including where Pace is behind.
- [Agent! (macOS26) vs Pace — macOS voice agent comparison](https://heypace.app/compared/agent-macos26.md): Agent! (macOS26) vs Pace for macOS: Pace is push-to-talk only (no hotword) and ships a tighter on-device default. Agent! wins on hands-free wake and provider breadth; Pace wins on trust surfaces, memory design, and the on-device-first posture being the default rather than one of 18 options. Screen-aware voice agents compared, including where Pace is behind.
- [Cursor Voice vs Pace — macOS voice agent comparison](https://heypace.app/compared/cursor-voice.md): Cursor Voice vs Pace for macOS: Pace is fully on-device; Cursor Voice round-trips every turn through OpenAI's Realtime API. Cursor Voice has barge-in and wake word — both things Pace lacks. Pace wins on privacy and zero per-turn cost. Screen-aware voice agents compared, including where Pace is behind.
- [Dottie vs Pace — macOS voice agent comparison](https://heypace.app/compared/dottie.md): Dottie vs Pace for macOS: Dottie ships 134 tools and a wake word — both ahead of Pace. The desktop app source is not public (only the dotbot SDK engine is MIT). Pace is fully open source with a tier picker and trust surfaces Dottie doesn't surface. Screen-aware voice agents compared, including where Pace is behind.
- [Fazm vs Pace — macOS voice agent comparison](https://heypace.app/compared/fazm.md): Fazm vs Pace for macOS: Fazm uses the Accessibility API for screen understanding (more reliable, more token-efficient than Pace's VLM-screenshot approach). But Fazm's STT and TTS go through Deepgram's cloud despite 'local' marketing. Pace is fully on-device, including speech. Screen-aware voice agents compared, including where Pace is behind.
- [Vox vs Pace — macOS voice agent comparison](https://heypace.app/compared/vox.md): Vox vs Pace for macOS: Vox is a true on-device peer to Pace with 48 tools and a passphrase mode Pace doesn't have. Pace has the tier picker, two-tier thread memory, recipe library, and watch mode that Vox doesn't ship. Both are MIT and fully local. Screen-aware voice agents compared, including where Pace is behind.
- [RCLI vs Pace — macOS voice agent comparison](https://heypace.app/compared/rcli.md): RCLI vs Pace for macOS: RCLI's MetalRT engine hits sub-200ms latency and 550 tok/s — a serious performance benchmark Pace should measure against. RCLI has local RAG Pace doesn't ship. Pace has the tier picker, trust surfaces, and MCP integration RCLI lacks. 1,523 stars — the most-trafficked on-device competitor. Screen-aware voice agents compared, including where Pace is behind.
- [Samuel vs Pace — macOS voice agent comparison](https://heypace.app/compared/samuel.md): Samuel vs Pace for macOS: Samuel's self-modifying plugin system and system-audio listening are genuinely novel — Pace has neither. But Samuel is fully cloud (OpenAI APIs). Pace is fully on-device. The plugin auto-repair loop is the most interesting idea here. Screen-aware voice agents compared, including where Pace is behind.
- [Shiro vs Pace — macOS voice agent comparison](https://heypace.app/compared/shiro.md): Shiro vs Pace for macOS: Shiro's parallel sub-agents and hybrid RAG knowledge graph are architecturally beyond Pace's single-thread agent loop. Pace has the tier picker, trust surfaces, and recipe library Shiro doesn't ship. Shiro's meeting mode is a surface Pace could add. Screen-aware voice agents compared, including where Pace is behind.
- [LocalNotch vs Pace — macOS voice agent comparison](https://heypace.app/compared/localnotch.md): LocalNotch vs Pace for macOS: LocalNotch shares Pace's notch surface but is text/image only — no voice input or TTS. It's a different interaction model. Pace is voice-first; LocalNotch is hover-and-type. The notch integration pattern is worth studying. Screen-aware voice agents compared, including where Pace is behind.
- [Cyclop One vs Pace — macOS voice agent comparison](https://heypace.app/compared/cyclop-one.md): Cyclop One vs Pace for macOS: Pace runs its default reasoning and vision stack on-device; Cyclop One requires the Claude API but has a more explicit plugin and remote-control architecture. Screen-aware voice agents compared, including where Pace is behind.
- [Peepbox vs Pace — macOS voice agent comparison](https://heypace.app/compared/peepbox.md): Peepbox vs Pace for macOS: Peepbox is built for unattended region watching and multi-agent workflows; Pace is voice-first, local by default, and uses a narrower synchronous approval loop. Screen-aware voice agents compared, including where Pace is behind.
- [BoBe vs Pace — macOS voice agent comparison](https://heypace.app/compared/bobe.md): BoBe vs Pace for macOS: BoBe centers on proactive observation and goals; Pace centers on push-to-talk, screen-referential requests, local approval, and a compact menu-bar surface. Screen-aware voice agents compared, including where Pace is behind.
- [Project Minimi vs Pace — macOS voice agent comparison](https://heypace.app/compared/project-minimi.md): Project Minimi vs Pace for macOS: Minimi is ambient memory for Claude, not a local voice agent loop. Pace is push-to-talk, screen-referential actions, and local models by default—without routing your agent loop through Claude. Minimi’s paid plan uses Gemini embeddings, so it is not pure local-only; Pace keeps the default path on-device. Screen-aware voice agents compared, including where Pace is behind.
- [docs](https://heypace.app/docs.md): This is the canonical documentation index for **Pace** — the on-device macOS menu-bar voice agent. Markdown committed to this repository is the source of truth. Blume renders it…
- [Pace FastPath — the native computer-use runtime](https://heypace.app/docs/architecture/computer-use-runtime.md): Pace's computer-use advantage is not the speed of an isolated click. It is the speed and reliability of the complete closed loop:
- [ADR-0001: Meeting audio capture approach — in-process SCStream](https://heypace.app/docs/architecture/decisions/meeting-audio-capture.md): Date: 2026-07-03 Status: Accepted
- [How Pace works, end to end](https://heypace.app/docs/architecture/how-it-works.md): This is a **learning-oriented** walkthrough of Pace for someone trying to understand the system, not a per-system spec. It follows a single interaction from the moment you speak…
- [Pace — architecture](https://heypace.app/docs/architecture/overview.md): 1. **Tinygpt's job is to provide Pace the BEST model for each role.** This is a mix of (a) training new specialists where no off-the-shelf model fits — LoRAs, distilled SLMs,…
- [Pace — architecture (systems reference)](https://heypace.app/docs/architecture/systems.md): This is the canonical detailed architecture reference for Pace — the per-system bullet list that previously lived inline in the repository AGENTS.md. It was extracted to keep…
- [Local Project State - 2026-06-02](https://heypace.app/docs/archive/local-project-state-2026-06-02.md): This checkout is now treated as a local Pace project.
- [Local Project State - 2026-06-03](https://heypace.app/docs/archive/local-project-state-2026-06-03.md): This is the current handoff snapshot for the local Pace project. The machine needed RAM kept free during this pass, so LM Studio was stopped and no model diagnostics or live app…
- [Smoke-test checklist — 2026-05-29 autonomous-loop changes](https://heypace.app/docs/archive/smoke-test-2026-05-29.md): After killall Pace && Cmd+R, walk through this list. Each item is self-contained: hold push-to-talk, say the prompt, look for the expected behavior, glance at the Xcode console…
- [Autonomous companion consolidation](https://heypace.app/docs/current/plans/autonomous-companion-consolidation.md): Status: handoff backlog Last reviewed: 2026-07-17
- [Pace-tuned planner v1 — training plan](https://heypace.app/docs/current/plans/pace-tuned-model-v1.md): Status: **export wired** — opt-in toggle in Settings → Models writes anonymized JSONL locally; copy into repo with scripts/export-pace-tuned-turns.sh. LoRA run still waits on…
- [Project Recommendation Context — Pace](https://heypace.app/docs/current/PROJECT_RECOMMENDATION_CONTEXT.md): Companion to PROJECT_STATUS.md for Starboard recommendations and fleet-wide product context. Per the fleet AGENTS.md standard, update this when product scope, major runtime…
- [Pace - Info.plist switch reference (local mode)](https://heypace.app/docs/development/info-plist-switches.md): See SETUP_LOCAL.md for the full local-mode recipe. This is the canonical summary of the Info.plist switches that control local VLM / planner / TTS / transcription behavior; it was…
- [Pace - Key Files](https://heypace.app/docs/development/key-files.md): This is the per-file reference for Pace's source, scripts, and bundled resources. It is the canonical home for the table that previously lived inline in the repository AGENTS.md;…
- [Open-source software in Pace](https://heypace.app/docs/development/open-source.md): Pace builds on maintained open-source components. Full copyright, license, and bundled notice text is available in **About → Open-source credits and licenses**, including offline.…
- [Test Coverage — EXEMPLARY Tier](https://heypace.app/docs/development/test-coverage.md): Pace holds itself to an **EXEMPLARY** testing standard. The project ships ~1435 Swift test cases across 156 test files, and coverage is measured on every CI run and available…
- [Dayflow Work Journal Snapshot](https://heypace.app/docs/knowledge/competitive/dayflow-work-journal-snapshot.md): Fetched: 2026-06-10 Source: https://github.com/JerryZLiu/Dayflow (README, dayflow.so)

Showing 50 of 86 pages; the catalog lists all public routes.

## Machine-readable

- [Full content](https://heypace.app/llms-full.txt): Bounded public page content
- [Markdown catalog](https://heypace.app/api/md/_catalog): All registered public routes
- [Agent catalog](https://heypace.app/api/ai): Existing discovery contract
- [AI usage policy](https://heypace.app/ai.txt): Permissions and attribution
- [Sitemap](https://heypace.app/sitemap.xml): Canonical HTML pages
- [OpenAPI](https://heypace.app/openapi.json): Public API contract