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

cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
L
LINUX DO - 最新话题
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Forbes - Security
Forbes - Security
博客园 - 司徒正美
Hugging Face - Blog
Hugging Face - Blog
W
WeLiveSecurity
Jina AI
Jina AI
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
N
News and Events Feed by Topic
V
V2EX
Stack Overflow Blog
Stack Overflow Blog
Engineering at Meta
Engineering at Meta
PCI Perspectives
PCI Perspectives
Martin Fowler
Martin Fowler
T
The Exploit Database - CXSecurity.com
F
Full Disclosure
WordPress大学
WordPress大学
S
Security Affairs
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
S
SegmentFault 最新的问题
P
Privacy International News Feed
IT之家
IT之家
M
MIT News - Artificial intelligence
G
GRAHAM CLULEY
Hacker News: Ask HN
Hacker News: Ask HN
D
DataBreaches.Net
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Google Online Security Blog
Google Online Security Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
C
Check Point Blog
美团技术团队
Security Latest
Security Latest
Cyberwarzone
Cyberwarzone
N
News and Events Feed by Topic
MyScale Blog
MyScale Blog
H
Help Net Security
宝玉的分享
宝玉的分享
The Hacker News
The Hacker News
The Last Watchdog
The Last Watchdog
The Cloudflare Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
爱范儿
爱范儿
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
I
Intezer
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
AI
AI
I
InfoQ
N
News | PayPal Newsroom
TaoSecurity Blog
TaoSecurity 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 - lotsoftick/hermes_client: Web client for Hermes agent
lotsoftick · 2026-04-27 · via Hacker News: Show HN

A web-based chat interface for the Hermes Agent by Nous Research. Manage multiple Hermes profiles as separate "agents", run conversations with full streaming, and configure cron jobs, skills, and plugins — all through a clean modern UI.

hermes_client_recording.mp4

Features

  • Multi-agent via Hermes profiles — every UI "agent" maps 1:1 to a Hermes profile, each with its own home directory, config, and sessions. Add, rename, and delete profiles from the UI; the corresponding hermes profile … commands run under the hood.
  • CLI-driven streaming chat — every turn spawns hermes -p <profile> chat -Q -q "<message>" and streams its stdout to the browser over Server-Sent Events. No hermes gateway required, no extra ports to open, no separate API server to babysit.
  • Cross-app session sync — sessions started in a standalone hermes REPL automatically appear in the sidebar within seconds. Continue a web-UI conversation from the terminal with hermes -p <profile> chat -r <sessionKey> and new turns stream straight back into the open chat.
  • Interactive setup terminal — an xterm.js drawer (backed by a tiny Python PTY bridge that ships with the API) hosts the real hermes -p <profile> model (and other config) commands when you create or reconfigure an agent, so API key wizards and arrow-key model pickers Just Work.
  • Brand model icons — each agent shows its provider's logo (OpenAI, Anthropic, Google, Mistral, OpenRouter, Nous, …) sourced from @lobehub/icons, with a one-click "configure model" prompt when none is set.
  • File uploads — drag files into the composer; they're stored under ~/.hermes_client/uploads/<conversationId>/ and Hermes is invoked with absolute paths via --image (for images) or referenced inline in the prompt (for everything else).
  • Cron, skills, plugins — surface Hermes' cron, skills list, and plugins list/enable/disable subcommands through the same UI shell.
  • User authentication — JWT-based auth with a default admin account created on first run.
  • Theming — built-in color themes with a sidebar picker; the interactive terminal inherits the active theme's sidebar palette.
  • Installable PWA — runs as a standalone desktop/mobile app via the browser's "Install app" feature.

Prerequisites

Verify Hermes is set up:

hermes --version
hermes status

That's it — no hermes gateway, no API_SERVER_* config, no shared API key. The backend resolves the binary itself via $PATH plus a curated list of fallback locations (~/.local/bin, ~/.hermes/hermes-agent/venv/bin, Homebrew prefixes…), so launchers like Finder, Cursor, and launchd work without a custom shell login.

If you keep hermes somewhere unusual, set HERMES_BIN in api/.env to its absolute path.

Platform notes

  • macOS / Linux — works out of the box.
  • Windows 10/11 — supported. Additionally requires:
    • Git for Windows (the auto-update flow uses git)
    • Visual Studio Build Tools (for the native module better-sqlite3).
    • Run PowerShell as Administrator the first time you execute npm start so that npm link can create the global hermes_client shim, and so that auto-start can be installed.

Quick Start

git clone https://github.com/lotsoftick/hermes_client.git
cd hermes_client
npm start

npm start builds everything, deploys to ~/.hermes_client, installs an OS-appropriate auto-start (macOS LaunchAgent, Windows Startup folder shortcut), and installs the global hermes_client command.

Service URL
Client http://localhost:18888
API http://localhost:18889
API Docs http://localhost:18889/api/docs

Note: API Docs (Swagger) are only available in development mode (npm run dev).

Default Login

On first startup, a default admin user is created:

  • Email: admin@admin.com
  • Password: 123456

Service Commands

After npm start, the hermes_client command works from any directory:

Command What it does
hermes_client start Start servers from ~/.hermes_client (no build)
hermes_client stop Stop servers
hermes_client restart Stop + start
hermes_client status Show service status
hermes_client uninstall Remove auto-start, global CLI, api & client artifacts (keeps database)
hermes_client uninstall --purge Also delete database (asks for confirmation)

To rebuild after code changes, run npm start from the repo again.

npm Scripts

Command Description
npm start Build, deploy to ~/.hermes_client, LaunchAgent, global CLI
npm run stop Stop servers
npm run dev API (nodemon) + Client (Vite) in dev mode with hot reload
npm run setup Generate api/.env only

Configuration

Ports (~/.hermes_client/.env)

Port configuration lives in a single user-level file at ~/.hermes_client/.env. It is created automatically on first run with sensible defaults.

Variable Default Description
API_PORT 18889 Port the API listens on
CLIENT_PORT 18888 Port the web UI uses

After changing a value, apply it with:

hermes_client restart       # production (installed via `npm start`)
npm run dev                 # development

API environment (api/.env)

Generated automatically on first run (see api/.env.example for reference):

Variable Default Description
NODE_ENV development Environment mode
JWT_SECRET (random) Secret for JWT signing (also authenticates /ws/pty upgrades)
DB_PATH ./data/hermes.sqlite Path to SQLite database file
PORT (API_PORT) API listen port (driven by ~/.hermes_client/.env)
ALLOWED_DOMAIN (unset — allow all) CORS allowlist, comma-separated; only enforced when HERMES_STRICT_CORS=1
HERMES_STRICT_CORS (off) Set to 1 to reject any origin not in ALLOWED_DOMAIN
API_PUBLIC_URL (derived from request) Optional fallback origin for upload URLs when no Host header
HERMES_BIN resolved automatically Override the absolute path to the hermes CLI binary
HERMES_HOME ~/.hermes Override Hermes home directory
HERMES_CLIENT_UPLOADS_DIR ~/.hermes_client/uploads Override where uploaded files are stored on disk

CORS / remote access. Hermes Client is a single-user local app. By default the API allows every origin and the client derives the API URL from window.location, so the same install works on localhost, on a LAN IP, and over Tailscale without any extra configuration. To lock it down to a fixed allowlist, set ALLOWED_DOMAIN and HERMES_STRICT_CORS=1 in api/.env (or ~/.hermes_client/api/.env for production installs).

The client picks its API origin at runtime: __HERMES_CONFIG__.apiBaseUrl (injected by the production static server from the request host) ▸ VITE_API_BASE_URL (build-time override) ▸ derived from window.location + VITE_API_PORT.

To regenerate secrets, delete api/.env and run npm run dev or npm run setup again.

Production Layout

When running npm start, built artifacts are deployed to ~/.hermes_client/:

~/.hermes_client/
├── api/
│   ├── build/          # Compiled API (JavaScript)
│   ├── node_modules/   # Production dependencies only
│   └── .env            # Auto-generated on first deploy
├── client/
│   ├── dist/           # Built static frontend
│   └── serve.mjs       # Lightweight static file server
├── data/
│   └── hermes.sqlite   # SQLite database (UI metadata + a mirror of Hermes session messages)
├── uploads/
│   └── <conversationId>/   # Files attached to messages, passed to Hermes by absolute path
└── hermes.log          # Combined log output

Hermes' own conversation state continues to live under ~/.hermes/ (sessions, skills, plugins, profiles…). The Hermes Client never writes there directly — it only invokes the hermes CLI and reads session JSON files for sync.

The source directory is only needed for building. Production processes run entirely from ~/.hermes_client/.

Install as an App (PWA)

Once the client is running, Chromium-based browsers (Chrome, Edge, Brave, Arc, Opera) detect that the app is installable:

  • An Install app banner appears in the sidebar — click it to install.
  • Alternatively, click the install icon in the address bar, or use the browser menu (More → Install Hermes…).

After install, the app launches in its own window (no tabs, own dock/taskbar icon) and behaves like a native desktop app. It still communicates with the local API server — the PWA is a UI shell, not a replacement for the background service.

Browser Support
Chrome / Edge / Arc Full — custom install banner, standalone window, auto-updates via service worker
Brave / Opera Full
Safari (macOS/iOS) "Add to Dock" / "Add to Home Screen" from the Share menu
Firefox Not installable (Firefox disabled PWA install on desktop); runs as a normal tab