The field

Pace isn't the only one doing this. Here's who else is, and what each one is actually good at.

A lot of macOS voice agents shipped in 2026. Most of them are interesting. None of them are Pace. This page is the honest version of that sentence — what each product does well, whether it's open source, and where Pace diverges (including the places where Pace is behind).

No checkmark grids. If you want a feature matrix, the repos are linked. What follows is the shape of each product in your head, the way you'd describe it to a friend.

The field splits three ways. Cloud agents round-trip every turn through someone else's servers. Hybrid ones default local but let you opt into cloud. On-device ones — the cluster Pace lives in — never leave your machine.

Cloud

3 products

Every turn hits someone else's data center. Fast to ship, costs per turn, needs an account.

Clicky / HeyClicky

www.heyclicky.com

AI teacher that lives next to your cursor. — Farza Majeed

STT · AssemblyAI streaming Reasoner · Claude Sonnet 4.6 (SSE) TTS · ElevenLabs Screen · yes

What it's good at

  • Background agents that run while you keep working — build a Mac app, file a Linear ticket, draft a Gmail.
  • YC S26, $10.1M raised, $20/mo Pro tier — the polished, distributed one.
  • Native Notion / Gmail / Google Calendar / Linear integrations out of the box.

Where Pace differs

Pace is fully on-device and one-time $29; Clicky is cloud-per-turn and a subscription. Clicky's background agents and onboarding polish are ahead of Pace today.

Cursor Voice

github.com/cursorvoice/cursor-voice

Native macOS voice assistant next to your cursor, powered by OpenAI Realtime API. — cursorvoice

STT · OpenAI Realtime API Reasoner · OpenAI Realtime API (gpt-realtime) TTS · OpenAI Realtime API (built-in voices) Screen · yes

What it's good at

  • Barge-in with echo rejection — interrupt the AI mid-response by talking over it.
  • On-device wake word ("Hey Cursor") via SFSpeechRecognizer, then cloud Realtime API for the conversation.
  • Built-in web_search tool without requiring an API key.

Where Pace differs

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.

Samuel

github.com/sambuild04/screen-voice-agent

Voice-first AI companion — wake-word activated, sees screen, hears system audio, writes plugins. — sambuild04

STT · OpenAI Realtime API Reasoner · OpenAI Realtime API + GPT-5.5 (plugin generation) + GPT-4o Vision TTS · OpenAI Realtime API Screen · yes

What it's good at

  • Self-modifying — writes and hot-loads its own plugins at runtime using GPT-5.5.
  • Auto-repair — detects plugin failures and patches code automatically (up to 2 attempts).
  • Hears system audio via ScreenCaptureKit with PID-level filtering, not just microphone.

Where Pace differs

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.

Hybrid

6 products

Local by default, cloud when you ask for it. The middle path — flexible, but the privacy posture depends on which tier you picked.

OpenClicky

github.com/jasonkneen/openclicky

The other open-source Clicky fork, by Jason Kneen. — Jason Kneen

STT · Configurable (AssemblyAI / OpenAI / Apple) Reasoner · Claude or local TTS · ElevenLabs or local Screen · yes

What it's good at

  • Sparkle OTA updates via signed appcast.xml — real auto-update distribution.
  • Agent Mode dashboard for coding, research, writing, and automation tasks.
  • Bundled skills, wiki seed, and Codex runtime in AppResources.

Where Pace differs

Pace is on-device-first with a tier picker; OpenClicky defaults to Claude + ElevenLabs. OpenClicky ships a signed DMG with Sparkle updates — Pace is still build-from-Xcode.

Impulse

github.com/section9-lab/Impulse

Native macOS assistant — sees, hears, remembers your projects. — section9-lab

STT · Speech framework (on-device) Reasoner · Any OpenAI-compatible / Ollama / LM Studio TTS · Local Screen · yes

What it's good at

  • 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.

Agent! (macOS26)

github.com/macOS26/agent

18 LLM providers, hotword-anchored, free on Apple Intelligence. — macOS26 / Todd Bruss

STT · SFSpeechRecognizer hotword Reasoner · 18 providers (Claude / GPT / Gemini / Grok / … / Apple FM / Ollama / vLLM / LM Studio) TTS · Local Screen · yes

What it's good at

  • Hotword-anchored dictation — say "Agent!" from across the room, hands-free.
  • 18 LLM providers wired in, BYO key, free forever on Apple Intelligence.
  • Apple AI as a real tool-calling agent — multi-step local tool calls, falls through to cloud only on failure.

Where Pace differs

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.

Dottie

www.dottie.ai

Free AI voice assistant — talk to your Mac, watch it work. — stevederico

STT · Local (MLX-based) Reasoner · Local MLX (3,800+ models) or cloud (OpenAI / Anthropic / xAI / Ollama) TTS · MLX Kokoro with premium AI voices Screen · yes

What it's good at

  • 134 built-in system tools for email, calendar, iMessage, music, and files.
  • Bundled inference stack with zero external dependencies — local Agent API on localhost.
  • "Hey Dottie" wake word + hold-to-dictate (Fn key).

Where Pace differs

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.

Fazm

github.com/mediar-ai/fazm

The fastest AI computer agent — controls your browser, writes code, handles documents. — mediar-ai

STT · Deepgram Nova-3 (streaming WebSocket) Reasoner · Claude (via ACP bridge) TTS · Deepgram Aura (7 languages) Screen · yes

What it's good at

  • Controls 300+ macOS apps via the Accessibility API — not screenshots, the structured UI tree.
  • Multi-language architecture: Swift desktop + TypeScript ACP bridge + Rust backend.
  • Real Chrome session automation — Gmail, Drive, Docs, Sheets, Calendar, WhatsApp.

Where Pace differs

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.

Shiro

github.com/abhisheksharma001/shiro

Local-first autonomous agent — watches screen, spawns parallel sub-agents, MCP ecosystem. — abhisheksharma001

STT · Deepgram Nova-3 (meeting mode) Reasoner · Local-first (LM Studio / Ollama) with Claude fallback TTS · Local Screen · yes

What it's good at

  • Parallel sub-agents with atomic SQL checkout, persona injection, depth & budget guards.
  • Hybrid RAG using sqlite-vec + FTS5 in one SQLite file — live knowledge graph updates on every tool call.
  • Meeting mode with ScreenCaptureKit audio capture + live action item extraction.

Where Pace differs

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.

On-device

6 products

Fully local. The cluster Pace lives in. Zero bytes off the machine, zero per-turn cost, works on a plane.

Ora

github.com/benedict2310/ora

Privacy-first macOS voice assistant, on-device AI. — benedict2310

STT · Parakeet (local) Reasoner · MLX + Qwen 3.5 VL TTS · Kokoro Screen · yes

What it's good at

  • Closest philosophical twin to Pace — fully local pipeline: Parakeet ASR → MLX Qwen 3.5 VL → Kokoro TTS.
  • Streaming pipeline with live transcription, streaming LLM tokens, and early TTS start.
  • Agentic tools across Calendar, Reminders, Contacts, Mail, Messages, Notes, and System.
  • Sparkle auto-updates and a downloadable release.

Where Pace differs

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.

OpenFelix

github.com/fspecii/openfelix

Voice-first AI agent for macOS that actually runs locally. — fspecii / @AmbsdOP

STT · On-device (Option+Space) Reasoner · MLX (Qwen / Mistral) TTS · Local Screen · yes

What it's good at

  • Cron jobs — schedule tasks with `daily@09:00`, `every:30m`, `once:ISO8601`.
  • Proactive alerts pushed to Telegram, Discord, and Slack.
  • Music generation via ACE-Step and YouTube spoken summaries.
  • Skill system that extends the agent to anything.

Where Pace differs

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.

ORB

github.com/settylokesh/ORB

Fully on-device voice agent — hears, sees, operates your Mac. — settylokesh

STT · Moonshine (ONNX Runtime) Reasoner · Gemma 4 E4B (4-bit, MLX) TTS · Local Screen · yes

What it's good at

  • Structured JSON action plans emitted by the VLM — explicit plan-then-execute loop.
  • ONNX Runtime + MLX dual runtime — Moonshine for ASR, MLX for the VLM.
  • Glow border around the screen to signal listening / planning / executing phases.

Where Pace differs

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.

Vox

github.com/vox-ai-app/vox

The first local AI that actually does things on your Mac — no cloud, no subscription. — vox-ai-app

STT · Local (via llama.cpp) Reasoner · Local (llama.cpp) TTS · Local Screen · yes

What it's good at

  • 48 built-in tools for email, iMessage, file management, and screen control.
  • Passphrase mode — text your Mac from any phone and get AI responses.
  • MCP client with stdio, SSE, and HTTP support + wake word with barge-in.

Where Pace differs

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.

RCLI

github.com/RunanywhereAI/RCLI

Talk to your Mac, query your docs — on-device voice AI + RAG, no cloud required. — RunanywhereAI

STT · Local — Zipformer (streaming), Whisper base.en, Parakeet TDT 0.6B Reasoner · Local — Qwen3 0.6B/4B, Llama 3.2 3B, LFM2.5 1.2B (MetalRT or llama.cpp) TTS · Local — Piper, KittenTTS, Matcha, Kokoro (28 voices) Screen · yes

What it's good at

  • Sub-200ms end-to-end voice latency via proprietary MetalRT GPU engine (up to 550 tok/s).
  • Local RAG over documents with hybrid vector + BM25 retrieval.
  • 20+ models across LLM, STT, TTS, VLM, VAD, and embeddings — all on-device.

Where Pace differs

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.

LocalNotch

github.com/arshawnarbabi/LocalNotch

Local AI assistant that lives in your MacBook's notch — chat, vision, file agent, all on-device. — arshawnarbabi

STT · None (text and image input only) Reasoner · Local (Ollama — user selects model) TTS · None (text output only) Screen · yes

What it's good at

  • Lives in the MacBook notch — hover to open, type to ask, then disappears. No window management.
  • Autonomous file-system Agent Mode with approval workflow.
  • Optional Brave Search with 3-layer hybrid classifier for automatic web search.

Where Pace differs

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.

The honest part

Where Pace is behind, not ahead.

No hotword. Clicky, OpenFelix, Ora, Agent!, Cursor Voice, Dottie, and Vox all have wake-word or hotkey hands-free activation. Pace is push-to-talk only. That's a real gap — hands-free is a feature people actually want, and Pace doesn't have it yet.

No background agents. Clicky's "clicky agent" runs multi-step tasks while you keep working — build an app, file a Linear ticket, draft a Gmail. Shiro spawns parallel sub-agents with depth and budget guards. Pace's agent mode is synchronous: it does the thing, then hands back control. Background execution is on the roadmap, not in the shipping product.

Smaller VLM. Pace uses a 2B screen-referential model. Ora runs Qwen 3.5 VL, ORB runs Gemma 4 E4B — both heavier and likely more accurate on dense screens. A "phone-a-friend" OCR tier for the heavy cases is the planned answer, not a shipping one.

Accessibility API for screen understanding. Fazm reads the structured AXUIElement tree instead of screenshotting — more reliable and more token-efficient than Pace's VLM-screenshot approach. Pace's VLM is more flexible (it can describe what it sees), but Fazm's approach is worth studying as a complement.

Latency. RCLI's proprietary MetalRT engine hits sub-200ms end-to-end voice latency and 550 tok/s. Pace hasn't published comparable benchmarks. This is the most-trafficked on-device competitor (1,523 stars) and sets the bar Pace should measure against.

Distribution. Ora, OpenFelix, and OpenClicky ship signed DMGs with Sparkle auto-updates. Pace now has a signed-DMG release path in the script (set PACE_DEVELOPER_ID + PACE_NOTARY_PROFILE), but no signed DMG has shipped yet — current releases are ad-hoc zips.

Scheduled + proactive surfaces. OpenFelix ships cron jobs and Telegram/Discord/Slack proactive alerts. Pace has the restraint-gated morning brief and watch mode, but the outbound-notification surface is narrower.

Self-modifying plugins. Samuel writes and hot-loads its own plugins at runtime, then auto-repairs them on failure. Pace's tool registry is static at launch. The self-repair loop is the most interesting idea here — Pace's recipe library is a fixed-catalog version of what Samuel does dynamically.

Rechecked June 2026.
If anyone shipped something I missed or got cheaper since, email me and I'll update this page.

The rest of the pitch — what Pace actually does — is on the landing page.

See Pace