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

Cisco Talos Blog
Cisco Talos Blog
V
V2EX
C
Check Point Blog
GbyAI
GbyAI
D
Docker
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
B
Blog RSS Feed
H
Hackread – Cybersecurity News, Data Breaches, AI and More
N
Netflix TechBlog - Medium
T
Troy Hunt's Blog
博客园 - Franky
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Microsoft Security Blog
Microsoft Security Blog
P
Privacy & Cybersecurity Law Blog
WordPress大学
WordPress大学
The Cloudflare Blog
S
SegmentFault 最新的问题
Latest news
Latest news
Microsoft Azure Blog
Microsoft Azure Blog
P
Proofpoint News Feed
I
InfoQ
博客园 - 【当耐特】
NISL@THU
NISL@THU
A
About on SuperTechFans
T
Tailwind CSS Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
The Hacker News
The Hacker News
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Scott Helme
Scott Helme
雷峰网
雷峰网
C
CXSECURITY Database RSS Feed - CXSecurity.com
Security Latest
Security Latest
V
Vulnerabilities – Threatpost
Security Archives - TechRepublic
Security Archives - TechRepublic
A
Arctic Wolf
Hacker News: Ask HN
Hacker News: Ask HN
N
News and Events Feed by Topic
IT之家
IT之家
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
aimingoo的专栏
aimingoo的专栏
T
Threat Research - Cisco Blogs
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
阮一峰的网络日志
阮一峰的网络日志
SecWiki News
SecWiki News
大猫的无限游戏
大猫的无限游戏
S
Security Affairs
The Register - Security
The Register - Security
www.infosecurity-magazine.com
www.infosecurity-magazine.com
L
LINUX DO - 热门话题
T
Tor Project 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 - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access — shell, file system, databases, APIs, secrets. But **nobody is governing what they actually do with it**. Frameworks like LangChain, CrewAI, AutoGen, and Claude Code give agents the power to execute. Agent Armor gives you the power to control, audit, and approve every single action before it happens. HN Vibes — Week 15, Apr 7–13 2026 GitHub - chojs23/ec: Easy terminal-native 3-way git mergetool vim-like workflow GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - JakOb-dotcom/cloud-sandbox-security-analysis: Technical analysis and Proof of Concept (PoC) regarding environment variable exfiltration in containerized cloud sandboxes via side-channel data leaks. Springboards - Flint Alpha Show HN: A simpler coding agent harness GitHub - audiodude/sudomake-friends GitHub - 256thFission/mini-mythos: OSS clone of Anthropic’s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome 应用商店 Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide GitHub - himanshudongre/smriti GitHub - sverrirsig/claude-control: macOS desktop dashboard for monitoring and managing multiple Claude Code sessions GitHub - ory/dockertest: Write better integration tests! Dockertest helps you boot up ephermal docker images for your Go tests with minimal work. Chiral - Chrome 应用商店 Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC GitHub - pmichaillat/latex-cv: Minimalist LaTeX template for academic CVs GitHub - oguzbilgic/posse: A web UI for Anthropic Managed Agents. GitHub - sshiraz/depsly: Dependency risk analysis tool for npm packages ABI Add safari/agent-harness — Safari browser automation via safari-mcp by achiya-automation · Pull Request #212 · HKUDS/CLI-Anything GitHub - Halfblood-Prince/trustcheck: Verify PyPI package attestations and improve Python supply-chain security GitHub - oguzbilgic/kern-ai: Agents that do the work and show it. GitHub - bruits/satteri: High-performance Markdown and MDX processing for the JavaScript ecosystem GitHub - tylergibbs1/feedstock: High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright GitHub - Grimm67123/grimmbot: The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling. GitHub - whitevanillaskies/whitebloom: Local whiteboard that blooms. GitHub - hwdsl2/docker-whisper: Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64). GitHub - yisding/reviewwiggum GitHub - MarwanAlsoltany/serrors: Structured errors for Go: sentinel hierarchies, typed data, custom formatting, and slog integration. GitHub - soatok/age-php GitHub - Luthiraa/markitme GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits GitHub - tombedor/excalicharts GitHub - wh1le/excalidraw-edit: Open and edit .excalidraw files from the terminal. Offline, auto-saves to disk. MalExt Sentry - Malicious Extension Scanner - Chrome 应用商店 GitHub - syi0808/asciianimesvg: Generate animated ASCII art SVGs from text. CLI, Rust library, WASM, and web editor. GitHub - zaina-ml/ml_forge: A visual-based graph node editor for training computer vision models. GitHub - anakin87/llm-rl-environments-lil-course: 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models GitHub - takaakit/superpowers-uml: Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling. AdriByte Studio - Sviluppo Web e Soluzioni Digitali GitHub - chouligi/angel-copilot: Your personalized Angel Investment Advisor Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 GitHub - agenteractai/lodmem: Level Of Detail Context Management for Agents GitHub - ostefani/subnetlens: A fast, concurrent network scanner with a TUI and plain-text CLI, built in Go. It discovers live hosts on your network, scans their open ports, resolves hostnames, and fingerprints operating systems—delivered. Cyber Pulse: Agentic Intel - Apps on Google Play Whisper API: Self-Hostable Speech to Text Transcription The Agent-Web Protocol Stack: A Research Thesis GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com – A searchable database of US Pardons GitHub - patrickdappollonio/dux: Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do. kMC Crystal Simulator Show HN: HyperFlow – A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: 🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. imgur.com GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. GitHub - nowork-studio/toprank: Open-source Claude Code skills for SEO, SEM, Google Ads GitHub - tacomanator/sash: Lightweight macOS menu bar app for reliably cycling through windows of the current application. Appents | Social Media Management for Product-First Teams GitHub - pnhoang/youtube-spam-blocker: Automatically detects and hides spam messages in YouTube Live chat. Set rate limits, keyword filters, and block repeat offenders. GitHub - decisionnode/DecisionNode: CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable. GitHub - AvaCodeSolutions/django-email-learning: An open source Django app for creating email-based learning platforms with IMAP integration and React frontend components. The $100K Gap in Kubernetes Security Tooling Function Calling Harness: From 6.75% to 100%
GitHub - frenchie4111/harness: Run a team of agents
frenchie4111 · 2026-04-29 · via Hacker News: Show HN

Harness

Run ten Claudes at once without losing your mind.
Ship more, faster, with every session at your fingertips.

Website · Download · Guide

Harness

Mobile mode

Harness running on a phone, with sidebar of agents and a terminal pane

Control your agents from your phone. Guaranteed to be better than Claude's shitty remote UI.

Browser control

Harness with an embedded browser tab the agent is driving

Give agents control of your browser. Useful for testing your code locally, or just ordering groceries.

→ Visit harness.mikelyons.org for screenshots, feature walkthroughs, and release notes.

Download

Grab the latest release from the releases page.

Installation

  1. Download the .dmg for your Mac architecture from the links above.
  2. Open the .dmg and drag Harness into your Applications folder.
  3. Launch Harness from Applications. The app is signed and notarized, so it should open without any Gatekeeper warnings.
  4. On first launch:
    • Pick a git repository when prompted.
    • Click the ⚙ gear icon in the sidebar and paste a GitHub personal access token (fine-grained or classic, with repo scope). This is optional but required for the PR status panel and checks.
    • When the hooks consent banner appears, click Enable so Harness can install status-tracking hooks globally at ~/.claude/settings.json. One install covers every worktree and is what makes the sidebar status dots reliable. Curious what the hook actually runs? See src/main/hooks.ts (the bash command built by makeHookCommand — it appends one line of JSON per event to /tmp/harness-status/<id>.ndjson) and src/main/agents/claude.ts (where the install/uninstall logic lives).

Requirements

  • macOS (Apple Silicon or Intel)
  • claude CLI installed and on your login shell's PATH
  • git installed (preinstalled on macOS via Xcode Command Line Tools)

Network access

Harness makes outbound network calls to two places: api.github.com (for PR status, check runs, and review state on worktrees that have an open PR) and this project's own GitHub releases feed (for auto-updates via electron-updater). If you have the gh CLI installed and authenticated, Harness will optionally pick up your token from it instead of requiring you to paste a PAT.

The optional remote-control WebSocket transport (used by the web client) is off by default, bearer-token-authed, and bound to 127.0.0.1 when enabled; opting in to LAN access (binding to 0.0.0.0) is a separate explicit config flag.

Uninstallation

  1. Remove the Claude Code hooks (do this while Harness is still running). Open Settings → AgentStatus hooks and click Remove hooks. This strips Harness's entries from ~/.claude/settings.json and leaves any user-authored hooks intact.

  2. Quit Harness with ⌘Q.

  3. Delete the app:

    rm -rf /Applications/Harness.app

    (or drag it to the Trash.)

  4. Remove app data (optional, for a fully clean uninstall):

    rm -rf ~/Library/Application\ Support/Harness
    rm -rf ~/Library/Preferences/org.mikelyons.harness.plist
    rm -rf ~/Library/Saved\ Application\ State/org.mikelyons.harness.savedState
    rm -rf ~/Library/Caches/org.mikelyons.harness
    rm -rf ~/Library/Logs/Harness
  5. If you skipped step 1 and already deleted the app, you can remove the hooks by hand. Open ~/.claude/settings.json and delete any hook entries whose object contains "_marker": "__claude_harness__" — every Harness-managed hook is tagged with that marker, so they're safe to identify and remove.

  6. Optional — clean up worktrees. Harness may have created git worktrees under claude-harness-worktrees/ next to your repos. These are normal git worktrees and aren't removed automatically. To clean them up:

    cd <your-repo>
    git worktree list
    git worktree remove <path>

    Or delete the claude-harness-worktrees/ directories from disk and run git worktree prune in each repo.

Features

  • Multi-agent — run Claude Code or Codex in the same window, one harness for both
  • Multi-repo — manage multiple repos in a single window, switch between them or see everything at once
  • Live PR status — see open PRs and CI checks for every worktree, auto-sorted by urgency
  • Embedded editor — full Monaco-powered editor for tweaking files without leaving Harness
  • Full code review tool — side-by-side syntax-highlighted diffs for every changed file in a worktree
  • Status at a glance — sidebar dots show which agent is working, waiting, or needs approval (powered by Claude Code hooks)
  • Command center — bird's-eye grid of every worktree with mini activity timelines
  • Tabs + vertical split panes — Claude, shells, and editor/diff tabs scoped to each checkout, splittable side-by-side
  • 9 themes — dark, dracula, nord, gruvbox, tokyo night, catppuccin, one dark, solarized dark/light
  • Configurable hotkeys — ⌘1–⌘9 to jump between worktrees, all rebindable
  • MCP: Claude controls Harness — a built-in MCP server lets Claude create and list worktrees on its own

Why did I build this

Honestly I have been using Conductor for a while as a fairly happy customer, but some rough edges have really started to annoy me so on a random Thursday morning I decided to build my own version of it that works the way I want to. Oh yeah did I mention:

Originally vibe coded start to finish — these days I occasionally crack open the actual source. Future travelers: still mostly vibes.

How's it work?

This app is specifically designed to be an easy way to do the sort of ADD fueled multi-worktree development that I have been in-to these days. Along the left you can see all the worktrees you have, and each worktree has it's own claude, additional terminals and PR display.

The main benefit of this is that your worktrees stay organized, and it's very obvious when one of your many claudes needs your attention (the dot will change colors)

Worktrees

This app assumes that you are going to want to use worktrees (otherwise what's the point)

It will create a worktree directory at ../<your repo folder>-worktree and start making worktrees there. This directory will probably be changable at some point

"Roadmap"

  • Initial functionality
  • Proper packaging into an app and dmg for other mac users
  • OTA Updates
  • Settings, configurability, etc
  • Better persistence (PTYs don't really stay if you kill the app, which can be a bit frustrating)
  • Multi-repo support
  • MCP server — Claude can create and manage worktrees itself
  • Command center — bird's-eye view of all worktrees
  • Activity tracking — visual timeline of agent status history
  • Syntax-highlighted diffs
  • 9 built-in themes
  • Support other LLM CLI tools — Codex is now supported alongside Claude Code
  • Per-agent model selection
  • Vertical split panes
  • Contextual system prompt injection so the agent knows it's inside Harness
  • Shared permissions via symlinked Claude settings
  • Release notes page inside the app
  • Browser panes — view localhost dev servers next to the terminal
  • Dev server management — start/stop/inspect dev servers per worktree
  • Notifications when claudes are ready for you (maybe peon noises?)
  • Mobile app
  • Whatever else people want — add a github issue or email me directly!

Setup, building, and running locally

Clone the repo and install dependencies:

git clone https://github.com/frenchie4111/harness.git
cd harness
npm install --legacy-peer-deps

The --legacy-peer-deps flag is required because electron-vite@5 declares a peer range that npm's strict resolver rejects against the installed vite@7.

Common commands:

Command What it does
npm run dev Launch the app in dev mode with hot reload
npm run build Type-check and build main, preload, and renderer to out/
npm run pack Build an unsigned .app for local smoke testing (fast — skips codesigning and notarization)
npm run dist:mac Full signed + notarized macOS build (requires .env with Apple creds)
npm run rebuild:dev Rebuild node-pty against the dev Electron version — run this if dev mode errors with posix_spawnp failed
npm run log Tail the debug log at ~/Library/Application Support/harness/debug.log

After npm run pack, you can launch the unsigned build with:

open release/mac-arm64/Harness.app

If Gatekeeper blocks the unsigned app, strip the quarantine attribute first:

xattr -cr release/mac-arm64/Harness.app

Contributing

I mean if you want? I think you probably just want to tell claude to download it and make whatever changes you want