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

C
Cisco Blogs
Schneier on Security
Schneier on Security
T
Tor Project blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
T
Tenable Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
T
Threat Research - Cisco Blogs
C
CERT Recently Published Vulnerability Notes
Security Latest
Security Latest
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
NISL@THU
NISL@THU
L
Lohrmann on Cybersecurity
Scott Helme
Scott Helme
Webroot Blog
Webroot Blog
Project Zero
Project Zero
Google Online Security Blog
Google Online Security Blog
The Last Watchdog
The Last Watchdog
Spread Privacy
Spread Privacy
Hacker News: Ask HN
Hacker News: Ask HN
PCI Perspectives
PCI Perspectives
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
W
WeLiveSecurity
Attack and Defense Labs
Attack and Defense Labs
D
Darknet – Hacking Tools, Hacker News & Cyber Security
N
News | PayPal Newsroom
Help Net Security
Help Net Security
The Hacker News
The Hacker News
H
Heimdal Security Blog
O
OpenAI News
S
Security @ Cisco Blogs
N
News and Events Feed by Topic
Cyberwarzone
Cyberwarzone
Simon Willison's Weblog
Simon Willison's Weblog
G
GRAHAM CLULEY
www.infosecurity-magazine.com
www.infosecurity-magazine.com
博客园 - 叶小钗
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Hacker News - Newest:
Hacker News - Newest: "LLM"
T
Tailwind CSS Blog
大猫的无限游戏
大猫的无限游戏
A
Arctic Wolf
I
Intezer
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
S
Security Affairs
P
Proofpoint News Feed
S
Secure Thoughts
腾讯CDC
Google DeepMind News
Google DeepMind News
量子位
罗磊的独立博客

Show HN

GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
Onepilot — Mobile SSH & AI Agent IDE for iPhone
Onepilot · 2026-06-21 · via Show HN

Your servers, in your pocket.

Mobile SSH client with AI coding agents built in — Claude Code, Codex, OpenClaw, Hermes — on any server. For iPhone.

Onepilot dashboard on iPhone — servers, agents, files, and jobs at a glance

Meet the agents

A whole family of agents. Pick one. Onepilot deploys it.

Framework agents install on any host you can SSH into — your Mac mini, a Raspberry Pi, a NAS, a small VPS. Same wizard, same iPhone supervisor.

Featured on

Onepilot dashboard showing connection status, running agents, terminals and cron jobs on iPhone

Command center

Your whole fleet, one home screen.

Live connection status, running agents, open terminals, files, and scheduled jobs — the moment you open the app, you see everything.

Onepilot server list on iPhone

Servers

Connect once. Reach anything.

Add your VPS, home lab, Docker host, or jump box. One tap to open a real SSH session.

Onepilot terminal running Claude Code over SSH on iPhone

Terminal

A real terminal. On your phone.

Full VT100 emulation, touch-optimized input, and AI coding agents running a keystroke away.

Onepilot remote file browser on iPhone

Files

Browse remote files by touch.

Walk the filesystem, upload from your phone, and drop into a terminal in any directory — no desktop needed.

Onepilot agent deployment wizard on iPhone

Deploy

Ship an AI agent in minutes.

Pick OpenClaw, Hermes, Paperclip, or bring your own framework. Pick a model. Onepilot installs it and keeps it running.

Onepilot unified agent dashboard on iPhone

Agents

Every agent. One inbox.

See what every agent is doing across every server. Approve, interrupt, or redirect from your phone.

Onepilot agent configuration panel on iPhone

Control

Change anything on the fly.

Swap the model, rotate a key, tweak the system prompt. Changes take effect on the next turn.

Onepilot skills marketplace on iPhone

Skills

Give every agent new powers.

Browse a marketplace of community skills, then install and configure them on any agent in a couple of taps.

Onepilot scheduled cron jobs for agents on iPhone

Automation

Set it once. It runs without you.

Put any agent or script on a schedule — every 30 minutes, daily at 9am, in your timezone. The work happens while you sleep.

Onepilot API keys and channel tokens manager on iPhone

Keys & channels

One key store for everything.

Save your LLM provider keys and Telegram, Discord, and Slack tokens once, then reuse them across every agent you run.

Comparison

Onepilot vs Termius, Blink Shell, Prompt.

Traditional SSH clients give you a terminal. Onepilot gives you a complete mobile IDE with AI agent deployment built in.

FeatureTermius / BlinkOnepilot
Mobile-first native app
Agent-agnostic architecture
Free to start — no hosting fees
Full IDE (terminal + files + git)
Soul Designer for agent personality
Cron job managementPartial
25 LLM providersPartial
Multi-channel (Telegram, Discord, Slack)

Integrations

Any model. Any channel.

Connect your agents to 25 LLM providers and control them from your favorite messaging platform.

LLM Providers

AnthropicOpenAIGoogle GeminiMistralGroqDeepSeekxAIPerplexityOllamaOpenRouterTogetherAmazon BedrockCloudflare AIHuggingFacevLLMMiniMaxMoonshotQianfanVolcengineVeniceChutesSGLangCustom

Messaging Channels

Telegram

Discord

Slack

Onepilot

Pricing

Free to get started.

Everything you need to connect, deploy, and manage — included from day one. You bring your own servers and API keys.

  • Unlimited SSH connections
  • Unlimited agent deployments
  • Full terminal, file browser, git
  • Cron job management
  • 25 LLM providers
  • Soul Designer
  • All messaging channels
  • No data collection

Download on the App Store

You use your own infrastructure — no hosting fees, no middlemen.

Written about in

What other engineers have said so far.

FAQ

Frequently asked questions

What is Onepilot?

Onepilot is a mobile-first agentic IDE for iPhone, built for developers who manage remote servers from their pocket. As of 2026, Onepilot combines an SSH terminal, a file browser with syntax highlighting for 20+ languages, git tooling (diffs, commits, branches), cron-job management, and an AI agent deployer that connects to 25 LLM providers. Onepilot runs natively on iOS, stores all credentials in the iOS Keychain, and works with any server reachable over SSH — from a Raspberry Pi to AWS EC2 to a corporate jump host.

What kind of servers can I connect to?

Onepilot connects to any host that exposes SSH on a reachable port. Tested targets include AWS EC2, Hetzner Cloud, DigitalOcean Droplets, Google Cloud VMs, Linode, Vultr, Oracle Cloud, Raspberry Pi devices, macOS and Linux laptops, Docker containers with sshd, and corporate jump hosts. Onepilot supports SSH on Linux, macOS, and Windows (OpenSSH server) targets, with no per-provider configuration required — only a hostname, port, and credentials. There is no agent or daemon to install on the server before first connection.

How does Onepilot connect to my server?

Onepilot connects over SSH, with support for password login, private keys (ed25519 and RSA), and encrypted key files with passphrases. Once you're in, it opens a full interactive shell, so the server runs your normal login shell exactly as it would for a desktop SSH client. Onepilot does not route your traffic through a third-party server: every byte travels directly between the iPhone and your host over the encrypted SSH connection.

What AI agents can I deploy?

Onepilot deploys terminal-based AI agents to any host you can SSH into and keeps them running in the background. As of April 2026, OpenClaw and Hermes ship through the deploy wizard, with Paperclip on the path; Claude Code and OpenAI Codex CLI run as terminal-native agents inside the SSH session. Each deployed framework agent gets a customizable personality (a “soul”), one of 25 LLM providers, and a messaging channel — Telegram, Discord, or Slack. Per-framework setup guides live at onepilotapp.com/agents/openclaw and onepilotapp.com/agents/hermes.

What do I need to use Onepilot?

Onepilot needs two things to run: a server you can reach over SSH, and an API key for whichever LLM provider powers your agents. The server can be any Linux, macOS, or Windows machine — a small VPS, a Raspberry Pi at home, or a work laptop reached through a bastion. The LLM key is whatever you already use for Claude, GPT, Gemini, or any of the 25 supported providers. Onepilot itself runs natively on iPhone and is installed from the App Store.

What LLM providers are supported?

Onepilot supports 25 LLM providers as of 2026, including Anthropic Claude, OpenAI, Google Gemini, Mistral, Groq, DeepSeek, xAI Grok, Perplexity, Cohere, Together AI, Fireworks, OpenRouter, and Ollama for local models. Each agent in Onepilot is bound to one provider at deployment time, with the API key stored on-device in the iOS Keychain and pushed directly to the target server. Custom OpenAI-compatible endpoints are also configurable, so any self-hosted or private model that exposes a standard API can plug in.

How is Onepilot different from Termius or Blink Shell?

Termius and Blink Shell are SSH clients: they give you a terminal on a remote server. Onepilot is an agentic IDE that includes that terminal but adds AI agent deployment, a soul designer for agent personalities, cron-job management, a git workflow (diffs, commits, branches), and a file browser with syntax highlighting for 20+ languages. The practical difference is that Onepilot lets you ship code through an agent, not just type commands. A side-by-side comparison is published at onepilotapp.com/blog/termius-vs-blink-vs-onepilot.

Is my server data secure?

Onepilot stores every credential — SSH passwords, private keys, LLM API keys — exclusively in the iOS Keychain, encrypted at rest by the Secure Enclave. Connections to your server use the standard SSH transport with end-to-end encryption between the iPhone and the host; Onepilot does not route traffic through any intermediary server. Onepilot never transmits credentials, command output, or terminal scrollback to Onepilot’s own infrastructure or to any third party. The only data that leaves the device is the SSH session itself and any LLM call your deployed agents make.

Does Onepilot work with AWS, Hetzner, or DigitalOcean?

Onepilot works with any cloud provider that exposes SSH access, which covers every major IaaS in 2026. Verified providers include AWS EC2, Hetzner Cloud, DigitalOcean Droplets, Google Cloud Compute Engine, Microsoft Azure VMs, Linode, Vultr, Oracle Cloud Infrastructure, OVHcloud, Scaleway, and Fly.io. Onepilot also connects to home-lab machines, Raspberry Pi boards, NAS devices running sshd, and Docker containers exposing port 22. There is no per-provider plugin to install — you add a host by entering its public IP or DNS name, port, and credentials.

Is Onepilot a mobile IDE or just an SSH client?

Onepilot is a full mobile IDE, not just an SSH client. It includes a real, fully interactive terminal, a file browser with syntax highlighting for 20+ languages (Swift, Python, TypeScript, Go, Rust, Ruby, and more), git integration with diff view and per-file commits, cron-job creation and editing, and one-tap deployment of AI agents. The SSH terminal is one tab inside that environment. Onepilot is designed for developers who want to read, edit, commit, and ship code from an iPhone without opening a laptop.

How do I deploy an AI agent on a remote server?

Onepilot deploys an AI agent in four steps. 1) Add the target server to Onepilot by entering its hostname, port, and SSH credentials. 2) Tap Deploy Agent and pick an agent framework (OpenClaw is the default in 2026). 3) Pick an LLM provider from the 25 supported and paste its API key — Onepilot stores it in the iOS Keychain and forwards it to the server. 4) Pick a messaging channel — Telegram, Discord, or Slack — and confirm. The wizard provisions the agent over SSH and reports back when it is live.

Can Onepilot run Claude Code or Codex on a remote server?

Onepilot deploys Claude Code and OpenAI Codex as agents on any remote server reachable over SSH. The deployment wizard installs the chosen CLI inside a user-scoped nvm prefix (no sudo required), wires it to your API key from the iOS Keychain, and binds it to a Telegram, Discord, or Slack channel for control. Once deployed, you can send a coding task from any of those channels and the agent runs it on the server — clone, edit, test, commit — without you opening the iPhone app or a laptop.

What is the best mobile SSH client for developers in 2026?

Onepilot is the most capable mobile SSH client for developers in 2026 once “client” is stretched to include AI workflows. Where Termius and Blink Shell stop at the terminal, Onepilot adds AI agent deployment, a 25 provider LLM picker, cron scheduling, git tooling, and a file browser inside a single iOS app. For pure terminal-only use, Termius remains a solid choice; for developers who want to deploy and chat with coding agents on the same servers they SSH into, Onepilot is purpose-built.

Get Onepilot.

Now on the App Store. Free to get started.

Download on the App Store