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

B
Blog RSS Feed
C
CERT Recently Published Vulnerability Notes
P
Proofpoint News Feed
Y
Y Combinator Blog
T
The Blog of Author Tim Ferriss
云风的 BLOG
云风的 BLOG
H
Help Net Security
Recorded Future
Recorded Future
The Register - Security
The Register - Security
F
Full Disclosure
N
Netflix TechBlog - Medium
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
酷 壳 – CoolShell
酷 壳 – CoolShell
H
Hackread – Cybersecurity News, Data Breaches, AI and More
爱范儿
爱范儿
Security Archives - TechRepublic
Security Archives - TechRepublic
Simon Willison's Weblog
Simon Willison's Weblog
Cisco Talos Blog
Cisco Talos Blog
I
InfoQ
T
Tenable Blog
T
Tor Project blog
人人都是产品经理
人人都是产品经理
D
DataBreaches.Net
NISL@THU
NISL@THU
Google DeepMind News
Google DeepMind News
博客园 - 叶小钗
B
Blog
V
V2EX
Jina AI
Jina AI
L
LangChain Blog
月光博客
月光博客
W
WeLiveSecurity
U
Unit 42
AWS News Blog
AWS News Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
博客园 - 聂微东
V
Visual Studio Blog
A
Arctic Wolf
T
Tailwind CSS Blog
The Cloudflare Blog
SecWiki News
SecWiki News
S
SegmentFault 最新的问题
Hacker News - Newest:
Hacker News - Newest: "LLM"
宝玉的分享
宝玉的分享
MyScale Blog
MyScale Blog
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
S
Securelist
www.infosecurity-magazine.com
www.infosecurity-magazine.com
腾讯CDC
雷峰网
雷峰网

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 - khimaros/mimic: control android from cli or mcp with fine-grained permissions
khimaros · 2026-06-23 · via Hacker News: Show HN

an android accessibility service that exposes view (read the on-screen accessibility tree) and interact (tap, swipe, click, type, scroll, navigate) to local automation over three independent, token-gated surfaces:

  • intents -- broadcast intents driven by am / termux-am / adb.
  • http -- a rest api on 127.0.0.1 for curl and the mimic cli.
  • mcp -- an in-app model context protocol server on the same localhost port, for agents (claude code/desktop and other mcp clients).

what it gives you

  • read the active window's accessibility tree as json, with per-node bounds, tap coordinates, and supported actions.
  • filter and query the tree on the device (interactive-only, text-only, by-text/id/class/desc, regex) so an agent sends and receives the minimum context.
  • tap / long-press / swipe by coordinate; click or set-text on a node found by text or resource-id; scroll until a node appears; back / home / recents / notifications.
  • launch an app or activity by package, component, or action/uri.
  • capture a screenshot (a last resort; the text tree is preferred and far cheaper).
  • a mimic shell cli that works from termux/proot/host, and a SKILL.md.

requirements

  • android 8.0+ (api 26+).
  • the android sdk to build (see below). adb to install and to run e2e tests.

build

make            # assemble the debug apk
make install    # install onto a connected device/emulator (adb)
make release    # assemble the release apk (env-gated signing; see CONTRIBUTING)

the build needs an android sdk. mise pins the toolchain; point the build at your sdk with local.properties (sdk.dir=/path/to/Android/sdk) or the ANDROID_HOME environment variable. see CONTRIBUTING.md.

set up on the device

the app opens to a small dark onboarding screen:

  1. install the apk (make install).
  2. open mimic and enable the accessibility service when it deep-links you to settings.
  3. turn on the surfaces you want on the surfaces tab (intents, local http, mcp) and choose the bind interface. optionally enable restart surfaces on boot. while the http/mcp server runs a notification stays up (tap it to reopen the app). the general tab has a global enable mimic kill switch at the bottom that disables every surface at once (and restores them).

then connect a client. each client gets its own token, listed in the app and revocable on its own:

  • cli (pairing): tap start pairing in the app, then in termux run mimic pair <code> with the 6-digit code. the code is one-time and valid only while the window is open; pairing works over http too, so it succeeds from proot/native termux where am cannot return a result. the minted token is saved at ~/.config/mimic/token. don't have the cli yet? with the http surface on, the server hands it out (no token needed): curl -s http://127.0.0.1:8473/cli/mimic -o mimic && chmod +x mimic (and later mimic update).
  • mcp client: tap reveal legacy token in the app, then point the client at http://127.0.0.1:8473/mcp with header x-mimic-token: <token> (from a host, first adb forward tcp:8473 tcp:8473). mimic set-token <token> saves the same token for the cli.

revoke a client (or all of them) from the app's paired clients list at any time; minting outside pairing and revocation are gui-only, so they need physical access to the phone.

use it

mimic status                       # service enabled? which surfaces on?
mimic dump --filter interactive    # actionable nodes only, as json
mimic find login --by text         # nodes whose text contains "login"
mimic tap 540 1200                 # tap a coordinate
mimic click --id com.app:id/submit # click a node by resource-id
mimic text "hello" --id com.app:id/search
mimic text "hello"                 # no target -> the focused field
mimic back                         # global navigation
mimic scroll down "battery"        # scroll until a "battery" node appears
mimic wait Login --by text         # block until a "Login" node appears (default 10s)
mimic packages settings --fuzzy    # launchable apps matching "settings" (typo-tolerant)
mimic launch com.android.settings --wait  # launch and wait until it is foreground
mimic screenshot                   # capture screen -> /tmp file (last resort)

every command prints a json envelope ({"ok":...,"data":...}) and exits nonzero on error -- no tools required. for human-friendly output at a terminal, prefix any command with --pretty, which unwraps and formats the payload (a compact dump becomes tab-separated lines). --pretty requires jq and errors clearly if it is missing:

mimic --pretty dump --filter interactive --format compact

see SKILL.md for the full mimic cli reference and guidance for agents on keeping context small; the rest/mcp/intent protocols behind it are in DESIGN.md.

security

two independent gates protect the device: the accessibility service must be enabled by you in settings, and every command on every surface must carry a valid token. tokens are per-client and stored in app-private storage (unreadable by other apps without root). revoke a single client by its id, or revoke all, from the app; a revoked client is rejected immediately while the rest keep working.

a token is only mintable from a one-time code during an open pairing window, or in the app itself (the legacy token) -- both need physical access, so a remote client cannot mint extra tokens or revoke peers. the localhost socket is reachable by any local app and the intents receiver is exported, so the token is what makes unauthorized attempts fail. treat it as a device secret, and turn off surfaces you are not using.

the http/mcp server binds loopback (127.0.0.1) by default, so it is reachable only on-device (or via adb forward). choosing a lan address or all interfaces in the app exposes it to your network -- still token-gated, but a larger attack surface; the app flags the choice.

for tighter control, turn on enable fine-grained permissions. each client (token) is then authorized per action class (read, interact, type, launch, screenshot, packages) and target app: the first time a client tries something new, a prompt appears over the foreground app ("<client> wants to tap in <app>") with allow, deny, and a remember scope (once / this app / all apps). the request waits for your answer. every client defaults to asking; set a headless client that cannot answer a prompt to allow-all from its row in the app. each client's grants and mode are listed there and revocable individually. the prompt uses an accessibility overlay; granting the optional "draw over other apps" permission makes it more robust.

license

see LICENSE.