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

A
About on SuperTechFans
D
DataBreaches.Net
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
V
Visual Studio Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
B
Blog RSS Feed
Recent Announcements
Recent Announcements
The Register - Security
The Register - Security
S
Secure Thoughts
Y
Y Combinator Blog
The Last Watchdog
The Last Watchdog
L
LINUX DO - 最新话题
V2EX - 技术
V2EX - 技术
腾讯CDC
GbyAI
GbyAI
G
Google Developers Blog
博客园 - 司徒正美
博客园 - 三生石上(FineUI控件)
T
The Exploit Database - CXSecurity.com
T
Threat Research - Cisco Blogs
P
Proofpoint News Feed
Schneier on Security
Schneier on Security
Microsoft Security Blog
Microsoft Security Blog
Jina AI
Jina AI
WordPress大学
WordPress大学
aimingoo的专栏
aimingoo的专栏
MyScale Blog
MyScale Blog
Help Net Security
Help Net Security
K
Kaspersky official blog
P
Privacy & Cybersecurity Law Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
AI
AI
MongoDB | Blog
MongoDB | Blog
Scott Helme
Scott Helme
J
Java Code Geeks
Engineering at Meta
Engineering at Meta
H
Heimdal Security Blog
H
Help Net Security
D
Darknet – Hacking Tools, Hacker News & Cyber Security
云风的 BLOG
云风的 BLOG
Microsoft Azure Blog
Microsoft Azure Blog
S
Security Affairs
TaoSecurity Blog
TaoSecurity Blog
The GitHub Blog
The GitHub Blog
Hacker News: Ask HN
Hacker News: Ask HN
Martin Fowler
Martin Fowler
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Project Zero
Project Zero
T
The Blog of Author Tim Ferriss
Last Week in AI
Last Week in AI

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 - joshduffy/claude-handoff-guard: Hook-enforced ownership for AI coding session handoffs
nahsuhn · 2026-05-30 · via Hacker News: Show HN

Hook-enforced ownership for AI coding session handoffs.

Most "handoff" tools solve amnesia: capture state to a markdown file, restore it after compaction or a new session. That problem is well covered. This one solves the problem nobody enforces: concurrent clobber. When two sessions work the same repo, or you resume on a second machine, or a background agent runs alongside an interactive one, they overwrite each other's handoff notes and you do not find out until the context you needed is gone.

The fix here is not a better template. It is a PreToolUse hook that makes a cross-session overwrite structurally blocked, not merely discouraged.

The core idea: the lock lives inside the file

Every handoff file's first line is an ownership marker:

<!-- claude-session: 9e0d3802-... -->

There is no sidecar .lock file. Ownership travels with the artifact through git, across devices, through a mv. A PreToolUse hook reads the calling session's id and compares it to the marker in the content being written and the marker already on disk. Mismatch blocks the write.

The chicken-and-egg (the interesting part)

To write a handoff that says who wrote it, the session needs to know its own id. It does not. The model has no native access to its session_id.

So the first write of a fresh handoff is designed to fail. The block reason carries the id:

Handoff write missing or wrong ownership marker.

Your session_id: `9e0d3802-4f...`.

Prepend exactly this as line 1:
  <!-- claude-session: 9e0d3802-4f... -->

Then retry.

The model copies the id from the failure and retries. One block per fresh handoff, and the file is now self-identifying for every future session. The missing capability becomes a one-time handshake.

Defense across all three mutation surfaces

A model that is blocked on Write will route around you. So the guard covers every way a file can be mutated:

  • Write validates the marker in the new content.
  • Edit validates the marker on disk (and blocks edits to legacy marker-less files until you take ownership with a Write).
  • Bash matches shell redirects to handoff paths (>, >>, tee, sed -i) and blocks unowned writes that try to sneak past the file tools.

It also accepts both the Claude Code tool schema (Write/Edit/Bash) and the Gemini CLI schema (write_file/replace/run_shell_command) in one hook, because gating on one silently disables the guard for the other client.

What ships

hooks/handoff-write-guard.mjs            PreToolUse: the ownership guard
hooks/handoff-session-start.mjs          SessionStart: surface existing handoffs + slug overlaps
hooks/handoff-stop-gate.mjs              Stop: once-per-session "you have no handoff" nudge
hooks/pre-commit-staged-marker-check.mjs git pre-commit: block commits mixing two sessions' handoffs
hooks/test/handoff-write-guard.test.mjs  node --test suite (8 cases)
scripts/handoff-migrate-archive.mjs      archive stale, marker-less legacy handoffs
scripts/install-git-hooks.sh             per-device installer for the pre-commit hook
skills/handoff/SKILL.md                  the /handoff slash command
rules/session-handoff.md                 the convention the hooks enforce
settings.example.json                    hook wiring to merge into ~/.claude/settings.json

Handoffs are expected under the standard Claude Code memory layout: ~/.claude/projects/<encoded-cwd>/memory/handoff-<branch>-<topic>.md, where <encoded-cwd> is the absolute working directory with /, \, and . replaced by -.

Install

# 1. Copy hooks/skills/rules into your ~/.claude
cp hooks/*.mjs        ~/.claude/hooks/
cp -r hooks/test      ~/.claude/hooks/
cp scripts/*          ~/.claude/scripts/
cp -r skills/handoff  ~/.claude/skills/
cp rules/*            ~/.claude/rules/

# 2. Merge settings.example.json into ~/.claude/settings.json (additive arrays)

# 3. Install the per-device git pre-commit hook (handoffs live in a git repo)
bash ~/.claude/scripts/install-git-hooks.sh

# 4. Verify
node --test ~/.claude/hooks/test/*.test.mjs

Philosophy: fail open, never trap the session

Every hook wraps its body in try/catch and exits 0 on any internal error. A bug in the guard degrades to convention; it never bricks a session. The Stop nudge is non-blocking and fires at most once per session. The escape hatches (touch /tmp/handoff-guard-bypass-<file>, or HANDOFF_GUARD_BYPASS=1) exist precisely because a structural guard you cannot override becomes a structural guard you rip out. Bypass use is logged so silent disabling is auditable.

Limitations (honest)

This makes the unaware clobber impossible. It does not make the chosen one impossible.

  • A session correctly shown a foreign marker can still archive the file or set the bypass env. Human review of the visible block message is the backstop for that class.
  • The <branch> token in a filename is not checked against the real branch (intentional: cross-device resume deliberately inherits a foreign branch's topic).
  • A TOCTOU race exists if two sessions create the same new filename in the gap between the hook's read and the tool's write. Vanishingly rare for solo dev; deliberately not locked.

License

MIT.