标签：#open

I run a production multi-agent AI system on a single M1 Mac in Jamaica. 6 autonomous agents. 26 cron workflows. 5-layer persistent memory. All containerized, all running 24/7. I checked my OpenRouter dashboard last week and realized something: I'd processed 2.4 billion tokens across 52 different AI models and spent a total of $0.52 . That's not a typo. Here's exactly where that money went and what it means. The Numbers Metric Value Total Requests 26,600+ Tokens Processed 2.4 Billion Models Used 52 Total Cost $0.52 Cost per Token $0.00000021 Tokens per Dollar 4.6 Million For context: GPT-4 Turbo costs about $0.00001 per token at scale. I'm running at roughly 50x below that rate. Where the $0.52 Actually Went Here's the breakdown by model: Model Requests Tokens Cost openrouter/owl-alpha 1,334 251.2M $0.00 nvidia/nemotron-3-super-120b 32 1.8M $0.00 google/gemma-4-31b-it 47 1.8M $0.00 openai/gpt-5 1 2.8K $0.03 google/gemini-3.1-pro-preview 1 3.2K $0.04 anthropic/claude-opus-4 1 2.0K $0.13 qwen/qwen3.5-plus 1 6.3K $0.01 z-ai/glm-5-turbo 1 3.0K $0.01 moonshotai/kimi-k2.5 2 4.1K $0.01 google/gemini-2.5-flash 2 5.5K $0.01 +42 other models ~125 ~8.5M ~$0.28 99.6% of my requests cost exactly $0.00. They ran on free-tier models or local inference. The $0.52 comes from a handful of premium model calls: Claude Opus, GPT-5, Gemini Pro. These are reserved for specific high-quality tasks — not everyday inference. What This Would Cost on Cloud Approach Hardware Monthly Cost Annual Cost My setup (M1 Mac) M1 Mac 16GB, local + free tier ~$0.09 ~$1.04 OpenRouter Paid Tier API-only, no local $15-30 $180-360 AWS (g4dn.xlarge + API) 1x T4 GPU, on-demand $350-500 $4,200-6,000 AWS (g5.xlarge + API) 1x A10G GPU, on-demand $700-1,000 $8,400-12,000 A $1,200 laptop replaces $500-1,000/month in cloud bills. The break-even point is about 2 weeks. How the Architecture Works The key insight: not every task needs a $20/month model . My system routes tasks intelligently: Local inference (free): Ollama

Webflow's code export has two problems. It is only available on paid Workspace plans, and even when you pay, it does not include your CMS content: collection lists export as empty states, collection pages export with nothing in them. If your site has a blog, the export gives you a site without a blog. Forms and search are disabled in exported code too, per Webflow's own docs. Meanwhile, the published site is sitting on a CDN, fully rendered. Every CMS page is real HTML. wget --mirror will happily fetch all of it. What wget gives you, though, is not deployable. I migrated a production Webflow site this way and hit the same five breakages everyone hits, so I turned the fixes into a Claude Code skill that runs the whole workflow. This post is the five breakages, because they are useful whether or not you use the skill, and they apply to Framer, Squarespace, and friends with different domain names. Setup: the mirror itself The one wget incantation that matters, because Webflow serves assets from a separate CDN domain and you have to tell wget to follow it: wget --mirror --convert-links --adjust-extension \ --page-requisites --span-hosts \ --domains = yourdomain.com,cdn.prod.website-files.com \ --no-parent https://yourdomain.com/ This downloads every page plus the CSS, JS, images, and fonts they reference, and rewrites URLs to relative paths. It looks complete. It is about 90% complete, and the missing 10% is invisible until the page renders blank. Breakage 1: the page renders blank, console says "integrity" The symptom: your mirrored page shows raw unstyled text or nothing at all, and the console says Failed to find a valid digest in the 'integrity' attribute . The cause is subtle. Webflow ships its <link> and <script> tags with SHA-384 SRI hashes. wget's --convert-links rewrites URLs inside the downloaded CSS files, which changes their bytes, which means the SRI hash no longer matches, which means the browser silently refuses to apply the stylesheet. The file is right

Most AI agent systems start with a simple idea: "Let's give the Agent Memory". At first, this usually means saving previous messages, retrieving similar chunks, and injecting them back into the prompt. That works for demos. It does not work reliably for real organizational workflows. Because chat history is not memory. A vector database is not memory. A bigger context window is not memory. Those are storage and retrieval mechanisms. Useful, yes. But memory in an AI Agent System is not just about remembering more information. It is about deciding what should influence future behavior. And that is a much harder problem. The Simple Version When people say "Agent Memory", they often mix together very different things: Conversation history User preferences Workflow state Previous tool results Retrieved documents Task summaries Business rules Approved policies Model-generated assumptions Evidence of completed actions But these should not all be treated the same way. A user saying "I usually prefer short answers" is not the same kind of memory as "invoice #123 was paid". A model saying "the client is probably interested" is not the same as a CRM record. A previous chat message is not the same as a runtime audit log. An approved company policy is not the same as a generated summary. When all of these are thrown into the same context window, the agent may look smarter for a while. Then it slowly becomes unreliable. More Context Can Make Agents Worse A common instinct is to give the agent more context. More history. More documents. More summaries. More retrieved chunks. More memory. But more context does not automatically mean better reasoning. Sometimes it means more noise. Sometimes it means stale information. Sometimes it means private information leaking into the wrong task. Sometimes it means the model starts treating old assumptions as current facts. Sometimes it means low-authority memory overrides high-authority evidence. This is one of the strange things about AI Age

The biggest lessons I learned from open source contributions weren't found in the code itself. Communication, collaboration, and workflows matter more than I expected. For a long time, I hesitated to contribute to open source. Part of it was because I assumed that contributing meant writing code. As a self-taught developer, that felt intimidating. The other part was "Git anxiety." Forks, branches, pull requests, merge conflicts, and CI checks all seemed like a lot to understand before I could even make a contribution. Eventually, I started small. Instead of focusing on code, I looked for opportunities to improve documentation, README files, and learning materials. What surprised me was that writing the actual change was often the easy part. Most of my learning happened outside the code itself: understanding contribution guidelines, repository workflows, automation, and review expectations. Over time, I realized that modern open source contribution is about much more than just writing code. Contribution Model Has Changed When many people think about open source contributions, the mental model is still fairly simple: Find Bug ↓ Write Code ↓ Open PR In reality, I realized that most modern repos involve much more than that. Before making a change, contributors often need to understand project workflows, CI pipelines, automated checks, contribution guidelines, and review expectations. The code change itself might only take a few minutes, while understanding how the repo operates can take much longer. A modern contribution often looks more like this: Understand Repository ↓ Understand Workflow ↓ Understand Automation ↓ Make Change ↓ Open PR ↓ Respond to Review It looks intimidating, but I think this flow helps projects stay maintainable as communications grow. What I've learned from contributing to different projects is that open source is not just a coding skill. It's also a collaboration skill. The faster you can understand how a project works, the easier it becomes to

Recently open-sourced by Microsoft, pg_durable is a PostgreSQL extension that enables durable workflows to run natively inside the database, eliminating the need for external orchestration systems. By Sergio De Simone

This is a follow-up to my earlier posts, and it is more of an open question than an answer. I have the data, I have a way to act, and I am genuinely unsure that acting is the right call. I could use the community's help thinking it through. Last week a supply-chain worm got into my GitHub account and repositories. I got out, cleaned up the proper way, and wrote it up. Then I checked the public list of repositories hit by the same worm, to see how the cleanup was going across the ecosystem. Nearly a week later, most of them are still carrying the live payload. It is worse than a count When you look closely, a lot of the owners are clearly trying. But they are missing how this actually works, in two ways that matter: Deleting is not removing. They remove the malicious files with an ordinary commit. That takes the payload off the branch tip, but the commit that introduced it is still in history, and the blob is still recoverable by anyone who reverts or checks out the old commit. The only real removal is rewriting history (reset, not revert) and asking GitHub to purge the objects, because the fork network keeps them reachable by SHA. One branch is not all branches. They clean the branch they know about and never see the backdated copies the worm planted on other branches, which are still live. And the part that genuinely worries me: some of these owners are almost certainly opening the infected repository in VS Code or an AI assistant to fix it , which is exactly the trigger that runs the payload again. The act of trying to clean it can re-detonate it. So: a large number of repositories still carrying a live credential stealer, and a large number of owners and contributors who do not know they are still exposed. The dilemma Here is where I am stuck. There are two paths and I do not like either. Report them to GitHub. Their response is automated and blunt. The repo gets disabled, with no human in the loop, the same hands-off automation that locked me out of my own accou

Your users have started asking ChatGPT and Perplexity instead of Google. So here is the uncomfortable question: when someone asks an AI engine "what is the best tool for <your category> ", does your product show up in the answer? Most founders have no idea. I didn't either, until I measured it — and the gap was nowhere near where I expected. So we built a CLI to measure it. It's called aeo-platform , it's MIT-licensed, it has zero runtime dependencies, and it runs entirely on your machine. This post is the five-minute version: install it, point it at your domain, and read the gap. I'll show you the exact commands and the real before/after numbers from running it on one of our own products. Quick framing on terms: AEO (answer engine optimization) is just SEO's younger sibling for AI answers — getting cited inside the AI's response instead of ranking on a SERP. Some people call it GEO. Same field. TL;DR — three commands npm install -g aeo-platform export OPENAI_API_KEY = "sk-proj-..." # required export GEMINI_API_KEY = "AIzaSy..." # required aeo-platform init --yes --brand = YOURBRAND --domain = YOURDOMAIN.COM --auto \ && aeo-platform run \ && aeo-platform report init auto-discovers your category and writes three commercial buyer queries to a local .aeo-tracker.json . run fires those queries at each engine and scores the answers. report opens a single-file HTML report in your browser. The whole thing installs in under a second (no dependency tree to resolve) and writes everything to disk under aeo-responses/YYYY-MM-DD/ — nothing is sent to a hosted dashboard. OpenAI and Gemini keys are mandatory (they also power a two-model cross-check that filters hallucinated brand mentions). Anthropic and Perplexity keys are optional — each one just adds a column to the report. What it actually measures A single run sends your buyer queries to four engines through their official REST APIs — no scraping, no proprietary black-box score: Engine Model Type ChatGPT (OpenAI) gpt-5-search

GitHub热门项目 | Concise, consistent, and legible badges in SVG and raster format | Stars: 26,767 | 55 stars this week | 语言: JavaScript

GitHub热门项目 | All-in-one Mail & Collaboration server. Secure, scalable and fluent in every protocol (IMAP, JMAP, SMTP, CalDAV, CardDAV, WebDAV). | Stars: 13,123 | 17 stars today | 语言: Rust

GitHub热门项目 | Low-level cross-platform audio I/O library in Rust | Stars: 3,797 | 3 stars today | 语言: Rust

GitHub热门项目 | ☄🌌️ The minimal, blazing-fast, and infinitely customizable prompt for any shell! | Stars: 58,253 | 99 stars today | 语言: Rust

GitHub热门项目 | ✨ Making your shell magical | Stars: 30,170 | 56 stars today | 语言: Rust

GitHub热门项目 | Search infrastructure for AI | Stars: 28,350 | 48 stars today | 语言: Rust

GitHub热门项目 | A minimal, secure Python interpreter written in Rust for use by AI | Stars: 7,519 | 165 stars today | 语言: Rust

GitHub热门项目 | An extremely fast Python linter and code formatter, written in Rust. | Stars: 47,898 | 17 stars today | 语言: Rust

GitHub热门项目 | The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable. | Stars: 22,310 | 38 stars today | 语言: TypeScript

GitHub热门项目 | Spec-driven development (SDD) for AI coding assistants. | Stars: 54,010 | 290 stars today | 语言: TypeScript

GitHub热门项目 | 🧡 Folo is the AI RSS Reader | Stars: 38,447 | 36 stars today | 语言: TypeScript

GitHub热门项目 | Create and share 3D architectural projects. | Stars: 16,576 | 69 stars today | 语言: TypeScript

GitHub热门项目 | One brain for all your agents | Stars: 637 | 47 stars today | 语言: TypeScript