标签：#open

Are you a data nerd who loves fitness? If you wear an Oura Ring or an Apple Watch , you’re sitting on a goldmine of biometric data. Specifically, Heart Rate Variability (HRV) —the secret sauce for understanding your nervous system's recovery status. But how do you know if a low HRV score is just a fluke or a serious sign of overtraining? In this tutorial, we are going to build a personalized HRV Anomaly Detector . Using Machine Learning , specifically the Isolation Forest algorithm from Scikit-learn , we will transform raw time-series data from the Oura Cloud API into an early-warning system for stress and burnout. This type of anomaly detection is essential for anyone looking to optimize their performance without hitting a wall. The Architecture 🏗️ Before we dive into the code, let's visualize how the data flows from your finger to our machine learning model. graph TD A[Oura Ring / Apple Watch] -->|Syncs| B(Cloud API / HealthKit) B -->|Fetch JSON| C[Python Script] C -->|Pandas Clean| D{Feature Engineering} D -->|HRV & Sleep Duration| E[Isolation Forest Model] E -->|Predict| F[Anomaly Flag: Overtrained?] F -->|Plot| G[Matplotlib Visualization] G -->|Insight| H[Rest or Push?] Prerequisites 🛠️ To follow along, you'll need the following stack: Python 3.9+ Scikit-learn : For our machine learning heavy lifting. Matplotlib : To visualize our "danger zones." Pandas : For time-series manipulation. Oura Cloud API : You'll need a personal access token (available at the Oura Cloud portal ). Step 1: Fetching Your HRV Data 🛰️ First, let's grab our data. If you don't have an Oura ring, you can export your Apple Watch data as a CSV, but the Oura API is much more convenient for automation. import requests import pandas as pd # Replace with your actual Personal Access Token TOKEN = ' YOUR_OURA_TOKEN ' url = ' https://api.ouraring.com/v2/usercollection/daily_readiness ' headers = { ' Authorization ' : f ' Bearer { TOKEN } ' } params = { ' start_date ' : ' 2023-01-01 ' , ' end_date '

TL;DR: This walkthrough shows how developers and coding agents can use Quantiles , an open-source AI evaluation platform licensed under Apache 2.0, to quickly run, analyze, and compare AI evaluations locally. We'll use the SimpleQA Verified benchmark as an example throughout this post, letting you follow the commands, inspect the evaluation results, and configure your own model for the same workflow. Running an AI evaluation is rarely as simple as sending prompts to a model. Developers must connect datasets, model APIs, scoring logic, result storage, and comparison tooling before they can answer a basic question: did the system get better? When those pieces are spread across scripts, notebooks, and logs, every rerun becomes harder to reproduce and diagnose. A score alone cannot reveal whether the model changed or whether the dataset, prompt, scorer, or sample set changed with it. Quickstart: Run an example benchmark The Quantiles CLI is called qt on the command line. A simple curl ... | bash command supports macOS and Linux on X86-64 and Arm64 systems. First, use it to install the CLI: curl -fsSL https://cli.quantiles.io/install.sh | bash If you don't want to run code directly sourced from the internet, see the install.sh source code first. Next, let’s run a built-in benchmark from start to finish using a single command. SimpleQA Verified is a 1,000-prompt benchmark created by Google DeepMind and Google Research. It re-curates questions from OpenAI's SimpleQA benchmark to reduce problems such as incorrect labels, topical bias, redundant questions, and ambiguous source evidence. Each example includes a short factual question in problem , its reference answer , topic and answer-type metadata, and supporting URLs. Use the following command to run simpleqa-verified using the built-in Quantiles demo model, which doesn't incur any usage charges: qt run simpleqa-verified Results from the demo model are intended only to demonstrate the evaluation workflow because its output

Cloud AI coding tools are powerful, but they also come with a bill, an API key, and a quiet upload of your source code to someone else's servers. What if your AI assistant ran entirely on your own machine instead? That is FLASH CLI (Fast Local Agent SHell): an AI-powered command-line assistant that talks to local or self-hosted Ollama models and can actually run shell commands for you. No API key. No subscription. No cloud. Why FLASH is different 100% local. It connects to an Ollama server, by default on localhost, so your code and prompts stay on your hardware. No keys, no bill. Ollama needs no API key, so there is nothing to pay for and nothing to leak. Truly agentic. FLASH does not just chat. It runs a real tool loop: it inspects your system, runs commands, searches the web, and shows its reasoning as it works. Model freedom. Point it at llama3.1, qwen2.5, mistral, or any tool-capable Ollama model, and swap with one setting. Local or remote. Set OLLAMA_HOST and the same client talks to a GPU box on your network or a server behind a reverse proxy. The four main tools FLASH gives the model a tight, powerful toolset: shell: run any command, non-interactively, with a timeout. web_search: pull live results from DuckDuckGo, built in. get_os: detect the operating system so it picks the right command every time. reason: surface a line of its thinking without ending the turn. It loops through plan, act, and observe until the job is done, then answers in rendered Markdown with syntax highlighting. Configuration Optional configuration lives in ~/.flash.env: MODEL=llama3.1 OLLAMA_HOST=http://localhost:11434 What it feels like Ask a question and let it work: [Flash]> what are the biggest files here? Thinking: check the OS, then find the largest files Retrieving operating system information Executing shell command: du -ah . | sort -rh | head -3 … Run a command yourself with the ! prefix, no AI in the loop: [Flash]> !git status On branch main nothing to commit, working tree cle

We Open-Sourced Both Halves of Our Security Stack — Detection and Deliberation AEGIS catches the threat. ENLIL decides what it means. Both are free, and we want to know if they actually help you. We've written before about each of these projects separately — AEGIS's post-quantum forensic logging and why ENLIL runs 9 LLMs in parallel instead of one . This post is about why they're actually one system, and why we're not gatekeeping either half of it. Two different jobs AEGIS is an intrusion detection/prevention system. It watches traffic, correlates signals across nine layers (from crypto-level filtering to adaptive moving-target defense), and decides — fast, locally, without calling out to anything — whether something is an attack. It's deliberately narrow: detection and containment, nothing else. No counterattacks, no active reconnaissance, one process, deployable on a standard VPS. ENLIL does the opposite job. It's slow by design — it convenes a council of independent LLMs, lets them reason in isolation (no model sees another's answer until synthesis), and produces a signed Decree: the majority view, the dissents, and a final verdict. It's built for the decisions where being fast and wrong is worse than being slow and right. Neither one replaces the other. AEGIS shouldn't spend 30 seconds deliberating about whether a SYN flood is a SYN flood. ENLIL shouldn't be making split-second network decisions. But there's an obvious seam between them: what happens when AEGIS catches something that isn't a simple yes/no — a pattern that's ambiguous, or severe enough that you want more than one model's opinion before you act on it? The Bridge That seam is a small connector: when AEGIS's detector layer flags something at high or critical severity, it fires a signed event at ENLIL's API. ENLIL convenes a tier of the council sized to the severity — a lighter tier for routine escalations, the full council (including the most expensive model) only for the things that deserve it. The

It's earnings season, and investors got an unpleasant surprise from Google: an increase on its spending estimate, to as much as $205 billion - from the last quarter's projection of up to $190 billion. Even the lower end of Google's new projected range - $195 billion - is much more than the company had previously […]

Github URL: https://github.com/SID-Technologies/Pilum In December 2025, I open-sourced Pilum , a multi-cloud deployment CLI that deploys to Cloud Run, Lambda, Azure, Cloudflare Pages, npm, Homebrew, and Docker Hub from a single pilum.yaml . The announcement post covered the architecture: recipes, ingredients, handlers, wave-based execution. That was the "it compiles and the tests pass" version. Three months and 40+ pull requests later, Pilum deploys all of SID Technologies , platform-core, Torch, Statio, every website, every npm package, and itself. This post is about everything that broke between "it works" and "it ships production software." ( Update: * there's now a seven-months-in addendum at the bottom. It's mostly about what stopped breaking.)* The Timeline Dec 2, 2025 : First commit. Baseline CLI with recipe system. (#1) Dec 4 : Homebrew release workflow. Pilum dogfoods its own deployment. (#2-#4) Dec 31 : Service graph, --only-changed , file embedding support. The "I need this for real" features. (#22-#24) Jan 3-12 : Documentation and bug fixes. The quiet "oh, this doesn't actually work" phase. (#25-#29) Feb 6-7 : The big feature sprint — 8 features in 48 hours. Wave deployments, npm recipe, Cloudflare Pages, Azure Container Apps, Cloud Run Jobs, environment variables, JSON output, history command. (#30-#38) Feb 8-12 : The big fix sprint — YAML parsing, package manager issues, build failures, error swallowing, GCP secrets, Cloudflare execution. Everything from the feature sprint broke something. (#42-#49) Feb 24 : Security hardening and npm publishing fixes. (#51-#53) Mar-Apr : Memory-based worker allocation, wave ordering bug, orchestrator rewrite. The "I thought this was done" phase. (#58-#62) The pattern is clear: features ship fast, fixes ship faster, and the real bugs show up a month later. Wave-Based Deployments Were Broken Wave-based deployment was the headline feature in #31. Services declare dependencies, Pilum builds a dependency graph, topological

Hands-On tests with 'UserHarbor' and IBM Bob: A Modular Approach to Python User Authentication and Permissions Introduction When evaluating open-source libraries for core application infrastructure - such as authentication, session management, and fine-grained Role-Based Access Control (RBAC) - getting hands-on with a complete reference application is invaluable. This is especially true for libraries aiming to be framework-agnostic, promising flexibility but requiring more explicit wiring. Recently, I wanted to explore UserHarbor ( github.com/userharbor/userharbor ), a lightweight Python user-management library designed without direct coupling to any web framework or database toolkit. Rather than manually bootstrapping a new project, setting up the SQLite database, and writing boilerplate code to explore every edge of the library, I used IBM Bob , to scaffold and implement an end-to-end reference demonstration integrated with FastAPI , SQLAlchemy for persistence, and SMTP (or a local console fallback) for transactional emails. The goal was to rapidly test UserHarbor's entire feature lifecycle - registration, email verification, session tokens, optional authentication, RBAC guards, password resets, and account deletion, which I personally find really useful. These capacities could be implemented in many applications and ease the phase of user registration, email validation etc… This post details the architecture built, highlights the key implementation logic, and illustrates how easily a decoupled core can be integrated into a modern web stack. UserHabor (from official GitHub repostory) Image from official project's repository Project status: UserHarbor is currently in an early stage of development. The API may change frequently. The library is not ready for production use yet . UserHarbor is a framework-agnostic Python library for user account management. Its goal is to provide a simple, stable, and framework-independent interface for common user-related operations:

Container-Native AI: Mastering GPU Passthrough, Memory Limits, and Auto-Scaling for Your Agent Infrastructure Unlock peak performance for your AI agents by mastering container resource management. This guide details Docker AI configurations for GPU passthrough, precise memory limits, and dynamic auto-scaling of containerized agents to build robust, cost-efficient AI infrastructure. The Container Imperative for AI Workloads The promise of AI agents—autonomous systems that reason, plan, and execute—hinges on reliable, scalable infrastructure. Deploying these agents on traditional VMs or bare metal creates inefficiencies: dependency conflicts, inconsistent environments, and manual resource provisioning that can't keep pace with demand. Container AI solves this by packaging agent code, models, and dependencies into immutable images, ensuring perfect reproducibility from a developer's laptop to production. However, containerizing AI isn't as simple as `docker run`. High-performance agents require specialized hardware access, particularly GPUs for model inference. They also demand strict resource boundaries to prevent one agent from starving others and efficient scaling to handle variable workloads. This is where container-native AI infrastructure moves beyond basic virtualization. By leveraging Docker's advanced features and orchestration platforms like Kubernetes, you can build a production-grade environment where GPU access is seamless, resource usage is optimized, and your fleet of containerized agents scales automatically. GPU Passthrough: Unleashing Accelerator Performance in Docker The single greatest performance hurdle for containerized AI is granting direct access to the host's GPU. NVIDIA's Container Toolkit is the standard solution, providing the necessary drivers and runtime hooks. Proper configuration allows a container to see and use the GPU with near-native performance, critical for low-latency inference. The setup begins at the host level, where you instal

Rust web development just got more interesting. If you prefer a video version: A few days ago, I spoke with Carl Lerche and Julien Scholz about Topcoat , a new batteries-included framework for building full-stack reactive web applications with Rust. Now I have finally tried it myself. Topcoat comes from the ecosystem behind Tokio and Axum, but it aims to provide a very different experience: routing, server-side rendering, reactive components, UI tooling, asset bundling, and hot reload in one framework. A simple Topcoat application This is what a basic application looks like: use topcoat ::{ Result , router ::{ Router , RouterBuilderDiscoverExt , page }, view ::{ component , view }, }; #[tokio::main] async fn main () { topcoat :: start ( Router :: builder () .discover () .build ()) .await .unwrap (); } #[page( "/" )] async fn home () -> Result { view! { <! DOCTYPE html > < html > < body > hello ( name : "World" ) </ body > </ html > } } #[component] async fn hello ( name : & str ) -> Result { view! { < h1 > "Hello, " ( name ) "!" </ h1 > } } The syntax feels surprisingly familiar if you have used server-rendered frameworks before. Pages and components are written in Rust, while the view! macro keeps the HTML structure easy to understand. What surprised me My first experience was better than expected. The setup was simple, the basic example was actually basic, and the development server provided working hot reload. That last part may sound normal to JavaScript developers, but it makes a huge difference for the Rust developer experience. Topcoat includes or plans to support: Server-side rendering Reactive components Module-based routing Tailwind integration Reusable UI components Asset bundling Fonts and icons Cookies and sessions Database integrations The experience feels closer to frameworks such as Laravel, Django, Rails, or Next.js, while allowing developers to build the application in Rust. Is Topcoat ready for production? Topcoat is still at an early stage. Break

Since launching last year, the startup today has more than 8 million people using the open-source or hosted version of its models, and now generates annual recurring revenue of $21 million.

GitHub热门项目 | ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work. | Stars: 2,491 | 983 stars this week | 语言: TypeScript

GitHub热门项目 | HTTP routing and request-handling library for Rust that focuses on ergonomics and modularity | Stars: 26,687 | 22 stars today | 语言: Rust

GitHub热门项目 | 🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs. | Stars: 2,372 | 218 stars today | 语言: TypeScript

GitHub热门项目 | 本地优先的跨平台 Claude Code / Agent 桌面工作台：多 Agent、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、任务感知桌面宠物，并支持微信、飞书、钉钉、Telegram、WhatsApp 与 H5 访问。 | Stars: 13,667 | 53 stars today | 语言: TypeScript

GitHub热门项目 | | Stars: 1,995 | 6 stars today | 语言: JavaScript

GitHub热门项目 | Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | Stars: 27,552 | 180 stars today | 语言: Python

GitHub热门项目 | "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/ | Stars: 7,129 | 91 stars today | 语言: Python

GitHub热门项目 | A curated list of awesome libraries, packages, strategies, books, blogs, tutorials for systematic trading. | Stars: 9,199 | 113 stars today | 语言: Python

This year I've built more MCP servers than I meant to, across three pretty different shapes: vellum : a self-hosted server over a folder of markdown, so my agent has a memory that's just files I own. (Open source, MIT.) Metrifyr : a marketing-data server that puts GA4, Search Console, AdSense and Tag Manager behind one connection. A read-only gateway over a company's internal user-data stack, federating half a dozen internal services behind one audited MCP surface. Personal, product, enterprise. Totally different data, totally different stakes. And yet the things that made each one good , versus a flashy demo that falls over the moment a real agent uses it in anger, were the same every time. Here are the seven that keep recurring. 1. Every tool you expose is a tax on the agent's context This is the one nobody warns you about. Every tool definition (name, description, JSON schema) gets loaded into the model's context on every single request , whether or not it's ever called. Twenty tools of boilerplate and the agent is reading pages of plumbing before it touches your data. So the design pressure runs the opposite way from a normal API: fewer, broader tools beat many narrow ones. vellum has 15 core tools and I fought to keep it there. If a tool doesn't earn its slot in the context window on most requests, it shouldn't be a tool. 2. Tools are for acting. Resources are for reading. The corollary to #1. Most servers expose everything (including "read this thing") as a tool. But MCP has a better primitive for reading: resources . In vellum, every note is a resource at a stable URI ( vellum://note/projects/x.md ). The agent attaches a document by reference instead of spending a tool round-trip to fetch it, and it can subscribe to that URI and get told the moment the note changes. Reading through a resource costs no tool definition. Reading through a tool costs one on every request. Use the right primitive. 3. Fail closed on auth, fail open on limits A token with no grants

After a lovely and productive conversation with your client, with still ringing ears, you check the coding agent's last log messages on a ticket that adds a discount to a product. The message was: "Done, I added the 10% discount and all tests pass. Stopping. " Well ... you know it's just not true, so you dig further and quickly realize that the discount functionality was never actually added and the tests it reported passing had never been run. The agent reached the end of the loop, looked at its own work, and called it finished. That call is the thing that shipped. This has a name. A paper published this June, From Confident Closing to Silent Failure , calls it false success: the agent asserts the task is complete while the actual state of the system says otherwise. It is common, and it holds up across capable models. On AppWorld, a benchmark for long-horizon coding agents, 75.8% of the runs that actually failed still ended with the agent claiming it was done. The researchers then put five different LLM judges on those completion claims, varying the prompts each time, and every one of them landed barely above a coin flip, because the thing each judge was reading was the closing sentence, and the closing sentence reads as confident whether the work happened or not. What told a real done apart from a false one turned out to be cheap and mechanical: a look at the actual state of the system. A lightweight deterministic state check caught four to eight times more false successes than the best of the judges. The paper has a name for the mechanism underneath, a hallucination of verification: the model narrates having checked something it never checked, and that narration is indistinguishable, sentence for sentence, from a report of a check that really ran. That gap, between what the agent said and what the system did, is what this piece is about. A loop runs five arms: generate, check, steer, retry, stop. The series opener named them; four pieces since took the check that