惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
爱范儿
爱范儿
J
Java Code Geeks
L
LangChain Blog
V
V2EX
大猫的无限游戏
大猫的无限游戏
S
SegmentFault 最新的问题
博客园 - Franky
Microsoft Azure Blog
Microsoft Azure Blog
Jina AI
Jina AI
Blog — PlanetScale
Blog — PlanetScale
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
The Cloudflare Blog
博客园 - 司徒正美
B
Blog
G
Google Developers Blog
Stack Overflow Blog
Stack Overflow Blog
罗磊的独立博客
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Apple Machine Learning Research
Apple Machine Learning Research
Engineering at Meta
Engineering at Meta
MyScale Blog
MyScale Blog
有赞技术团队
有赞技术团队
Hugging Face - Blog
Hugging Face - Blog

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - Vikrant-Khedkar/gingerpaw: Push-to-talk dictatio...
vikrant-gg · 2026-06-22 · via Hacker News: Show HN

GingerPaw

A multi-agent coding workspace for macOS — with on-device voice. Fully local.

Run a whole team of coding agents in parallel — Claude Code, Codex, Gemini CLI, Cursor — each in its own git worktree. Agents can even spawn their own workspaces and launch other agents. Plus push-to-talk dictation and a talking ginger cat that speaks (in a neural voice) when an agent finishes. Nothing ever leaves your Mac.

GingerPaw Agent Workspace — coding agents running in parallel across git worktrees


What it does

🖥️ Agent Workspace

Run multiple coding-agent CLIs side by side, each isolated:

  • A tab per agent — Claude Code, Codex, Gemini CLI, Cursor — real interactive terminals (SwiftTerm PTYs) running in-app.
  • Git worktrees — every workspace is a worktree on its own branch under ~/.gingerpaw/worktrees, so agents work in parallel with zero collisions.
  • Live diff panel — Files / Changes / Review with +/− counts, one-click Commit, and Create PR (via gh).
  • Ports + branch status — detected dev-server ports and ahead/behind, right in the status bar.
  • Agents launch with auto-approve flags — safe, because each is sandboxed to its own worktree.

🤖 Agents that orchestrate agents (MCP)

GingerPaw runs an MCP server, so an agent running inside a workspace can drive the cockpit: create new workspaces, launch other agents with a task, and read their diffs back. Ask one agent for something and a whole team shows up in your sidebar, working in parallel — all visible and steerable. A .mcp.json is auto-wired into every worktree (Claude Code) and ~/.codex/config.toml (Codex).

🐈 Voice + dictation

  • Push-to-talk dictation — hold Fn or Right Option, speak, release; transcribed on-device with WhisperKit and pasted into any app.
  • Talking-cat notifications — when a coding agent finishes, a ginger cat pops up and speaks a summary in a natural Kokoro (82M) neural TTS voice (or macOS say). Walk away and still know when it's done.

All on-device. No cloud, no account.

The talking cat announcing a finished task

Requirements

  • macOS 14+ (Apple Silicon)
  • Xcode 16+ with the Metal Toolchain (xcodebuild -downloadComponent MetalToolchain) — required to compile MLX's GPU shaders.
  • XcodeGen (brew install xcodegen)
  • The agent CLIs you want to use (claude, codex, gemini, cursor-agent) on your PATH.
  • gh (optional) for Create PR. Kokoro TTS (optional) for the neural voice.

Build

xcodegen generate                                    # project.yml -> GingerPaw.xcodeproj
xcodebuild -project GingerPaw.xcodeproj -scheme GingerPaw \
  -configuration Debug -derivedDataPath ./dd build

MLX requires Xcode's build system to compile the Metal kernels — a plain swift build will not produce the metallib. Use xcodebuild (or open the project in Xcode).

Run swift test inside Packages/FlowKit for the unit tests.

Permissions

GingerPaw needs three macOS grants (surfaced in the in-app Permissions tab):

Grant Why
Microphone Record your voice for transcription
Input Monitoring Detect the push-to-talk hotkey globally
Accessibility Paste text into the focused app

Architecture

A thin SwiftUI app shell (App/) over FlowKit (Packages/FlowKit), a SwiftPM package of focused libraries:

  • AgentWorkspace — the multi-agent window: SwiftTerm terminals, git worktrees, the diff panel, ports/PR, and the MCP bridge (MCPBridgeServer) that lets agents drive the app over a loopback socket.
  • AgentMCP — shared Codable types for the MCP bridge (kept dependency-light so the gingerpaw-cli MCP binary stays small).
  • AgentNotifications — the <say> transcript parser + speech service shared by the app and the gingerpaw-cli hook binary.
  • Dictation — the DictationCoordinator state machine · Audio · Transcription (WhisperKit) · TextInsertion.
  • TextProcessing — MLX/Qwen formatter (experimental) · Hotkeys (global CGEventTap) · Permissions (TCC) · Overlay · Settings.
  • AppCore — composition + UI: the Agent Workspace, Dictate / Voice / Permissions / Settings, and the talking cat.

gingerpaw-cli is the bundled helper binary: notify (the Claude Code voice hook) and mcp (the MCP server agents connect to).

License

MIT