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

罗磊的独立博客
Apple Machine Learning Research
Apple Machine Learning Research
The Cloudflare Blog
WordPress大学
WordPress大学
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
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 叶小钗
博客园 - 聂微东
阮一峰的网络日志
阮一峰的网络日志
腾讯CDC
博客园 - 三生石上(FineUI控件)
V
V2EX
有赞技术团队
有赞技术团队
V
Visual Studio Blog
小众软件
小众软件
Jina AI
Jina AI
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - Franky
量子位
T
Tailwind CSS Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
P
Palo Alto Networks Blog
Cisco Talos Blog
Cisco Talos Blog
I
Intezer
Project Zero
Project Zero
A
Arctic Wolf
P
Privacy International News Feed
V
Vulnerabilities – Threatpost
L
Lohrmann on Cybersecurity
S
Securelist
C
Cybersecurity and Infrastructure Security Agency CISA
C
CXSECURITY Database RSS Feed - CXSecurity.com
T
Tor Project blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
S
Security @ Cisco Blogs
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Google DeepMind News
Google DeepMind News
N
News and Events Feed by Topic
TaoSecurity Blog
TaoSecurity Blog
L
LINUX DO - 热门话题
G
GRAHAM CLULEY
Help Net Security
Help Net Security
N
News | PayPal Newsroom
W
WeLiveSecurity
G
Google Developers Blog
Microsoft Security Blog
Microsoft Security Blog
Engineering at Meta
Engineering at Meta
MongoDB | Blog
MongoDB | Blog
C
Check Point 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%
Introducing Open Public
goodroot · 2026-05-21 · via Hacker News: Show HN

Coding agents have changed how software is written. Many developers are all-in. Companies large and small are throwing as much cash as they can find at model tokens. The impacts are complex, massive, and everywhere.

In this new era, GitHub activity tells quite the story:

"[GitHub] platform activity is surging. There were 1 billion commits in 2025. Now, it's 275 million per week ... GitHub Actions has grown from 500M minutes/week in 2023 to 1B minutes/week in 2025, and now 2.1B minutes so far this week." — Kyle Daigle, COO, GitHub, April 4, 2026

GitHub activity surge chart comparing commits and Actions minutes

This flood brings a lot of good with it. It also brings swells upon swells of new maintenance pressure. New repository issues are long, numerous, and verbose. New contributors are zealous and plentiful, with large PRs full of massive new line counts.

Even with the resources and talent of a strong team, it is hard to keep up. It does not feel sustainable. And what about the projects run by volunteers? The open source maintainers and projects without whom software as we know it, and our beloved internet, would not work?

Open source and the agentic flood

Software depends on open source. The humble maintainer, historically underappreciated and underpaid, now has to struggle to stay afloat in this new world whether they use agentic coding tools or not.

As great as hyper-intelligent bug finders and contributors are, parsing through all of this information is often exhausting. Some of the more popular projects have turned off their issue queues and PR permissions outright in response.

For those that have embraced these new tools, the rising prices of quality compute mean that, along with their free time, they now need to burn their own cash to keep up. This makes us uneasy. Many of us cannot shake the feeling that this initial "generally affordable" period of frontier model usage will not last. What then?

Something has got to give. These people and projects need more support.

That's where we come in...

Introducing Open Public (opub)

We link donors to open source projects. Donations fund donated compute for over 30 leading agentic coding models. Token usage is public. Donors know their generosity went toward the projects they support.

When donations are received, capped compute keys provide maintainers with a fast, reliable stream of compute to fuel whatever will help them keep up.

They might use GitHub's Copilot CLI to manage GitHub issues and PRs, Continue to review and audit incoming PRs, or spend raw tokens for development and fixes through popular harnesses like Claude Code, OpenAI Codex, Mistral Vibe, or OpenCode.

Spend events roll back to the opub project page, so donor impact is visible in the project ledger. If a maintainer's agentic session starts through the opub open source CLI, compute usage is considered Linked: donors can see that spend was tied to the compute key and project session they funded.

The juice to stay afloat

Maintainers already have work that donated compute can help with.

A donor might want to help a project close stale bugs, review a backlog of pull requests, improve tests before a release, investigate a security report, ship a desirable feature, or modernize documentation. Open Public provides a way to do so by directly empowering the maintainers at the heart of the project.

We turn donations into compute: tokens, the juice, the fuel of agentic coding.

Through opub, the unit of trust is at the project level:

  • an opub project represents and verifies a public GitHub repository + maintainer
  • a donation funds one project's compute balance
  • maintainers make capped compute keys to consume the balance
  • token spend appears within the public project ledger
  • if the CLI is used, Linked sessions show funded compute was launched from the right project context

Donation to project balance to capped compute key to token spend and linked session

To correlate spend with the project, we do not need to observe prompts, responses, diffs, files, commits, or pull requests. It's a clean, transparent way to ensure the projects you appreciate and rely on won't fall behind the agentic flood.

The founding round

Our goal is to amplify the health of the open source ecosystem. Any public GitHub repository can register now. To celebrate our launch and welcome project maintainers, the first 20 eligible verified projects with 100 or more stars get $50 in starter donated compute from opub.

Register now

After registration, connect a GitHub repository to receive your own Open Public project page. Projects outside the starter donated compute offer are welcome too: register, share the page, receive donations, and create compute keys once the project has available balance.

Our next mission? Find you some generous donors. To help, you can share your project page on social media, put it into your README, and point your community to it when people ask how to support the project. We'll do our best to surface projects and provide exposure wherever possible.

Once someone has donated to your project, you can create a key and securely apply that compute through leading models such as:

  • Claude Sonnet 4.6 (anthropic/claude-sonnet-4.6)
  • Claude Haiku 4.5 (anthropic/claude-haiku-4.5)
  • GPT-5.5 (openai/gpt-5.5)
  • GPT-5.4 (openai/gpt-5.4)
  • GPT-5.4 Mini (openai/gpt-5.4-mini)
  • GPT-5.3 Codex (openai/gpt-5.3-codex)
  • Codestral 2508 (mistralai/codestral-2508)
  • Devstral (mistralai/devstral-2512)
  • MiniMax M2.5 (minimax/minimax-m2.5)

There are over 30 models at various costs, all served at their standard rates.

See the documentation for the full list of Available models.

What maintainers can do

After a project has available balance, a verified maintainer creates a compute key with a dollar limit. The limit is chosen by the maintainer and reserved from the project balance. Multiple active compute keys are allowed, so a project can keep setup flexible, rotate keys, or separate workflows without exposing unlimited spend.

Each key is shown once in the browser. After that, the secret belongs in the maintainer's local credential store or direct tool configuration.

The key can be used two ways:

  1. run a supported agent through the opub CLI for a Linked session
  2. paste the key into any compatible OpenAI-formatted workflow for direct, unlinked use

Both paths spend from the project balance. The CLI path appends a Linked badge. That way, donors can see when compute was spent through a linked project session.

Linked sessions

Session linking is not required, but it sends a strong signal to donors.

The opub CLI wraps the agent harness launch:

opub setup codex --project owner/repo --compute-key-id ck_...
opub run codex

opub setup stores the capped compute key in the system credential store and writes non-secret agent configuration. opub run starts the agent with the right credentials and refreshes a local, secretless MCP session for project context.

That session context can say which project, compute key, and agent were launched. It does not prove what the maintainer typed, what the model answered, which files changed, or which issue was fixed.

We do not and will not observe, train on, or collect prompts or prompt responses. Our method of session linking is open source and relies on MCP and agent-side skills to report session state. Donors get a useful public signal without turning maintainers' workspaces into surveillance systems.

The CLI supports popular agentic coding harnesses such as:

  • Claude Code (claude)
  • Codex (codex)
  • GitHub Copilot CLI (copilot)
  • Vibe (vibe)
  • OpenCode (opencode)
  • Continue (continue)

The API key can also be used directly with OpenAI-compatible tooling. That path is unlinked, but spend still accrues to the project balance.

What comes next

We're excited to see what the creators of our favorite projects can do with greater access to today's leading coding models. We know this isn't for everyone, and there's no pressure for project maintainers to register if they would rather not use agentic compute. But for those who are willing to use these new tools, we're excited to work with you to eliminate or reduce your agent-based costs.

This blog will publish content to help maintainers get the most out of donated compute, and profile the maintainers using it to build and refine the great things we have relied on in the past and will rely on tomorrow.

May no maintainer be left behind.

Subscribe to the newsletter

Engaging content and essential product updates.

Concise updates on our latest writing, sponsorships, and updates.