标签：#rce

We’ve all been there. You click "Export Health Data" on your iPhone, wait ten minutes, and receive a massive, bloated export.xml file. If you've tracked your fitness for years, this file can easily exceed 5GB. Try opening that in Python’s ElementTree or even pandas , and your RAM will cry for mercy. This is a classic Data Engineering challenge: transforming high-volume, semi-structured XML into actionable insights without waiting an eternity. In this tutorial, we are going to build a high-performance parser using Rust performance techniques, Rayon for parallelism, and ClickHouse for lightning-fast OLAP queries. By leveraging Rust's zero-cost abstractions, we'll turn a 20-minute Python slog into a sub-30-second sprint. 🚀 The High-Level Architecture Handling 5GB of XML requires a streaming approach. We cannot load the whole file into memory. We will stream the XML, parse segments in parallel, and ship them to ClickHouse using Protocol Buffers for maximum serialization efficiency. graph TD A[Apple Health export.xml] --> B[Streaming XML Reader] B --> C{Chunking Logic} C -->|Batch 1| D[Rayon Worker 1] C -->|Batch 2| E[Rayon Worker 2] C -->|Batch N| F[Rayon Worker N] D & E & F --> G[Protobuf Serialization] G --> H[(ClickHouse DB)] H --> I[Grafana / SQL Insights] Prerequisites To follow along, you'll need: Rust (Stable) Tech Stack : quick-xml (for streaming), serde (serialization), rayon (data parallelism), and clickhouse-rs . A running ClickHouse instance. 1. Defining the Data Schema Apple Health data (specifically Record types) consists of types, dates, and values. Since we want high performance, we'll use Protocol Buffers to define our intermediate format, ensuring minimal overhead when moving data through the pipeline. // Simplified representation of a Health Record use serde ::{ Deserialize , Serialize }; #[derive(Debug, Serialize, Deserialize, Clone)] pub struct HealthRecord { #[serde(rename = "@type" )] pub record_type : String , #[serde(rename = "@startDate" )] pub

I run a local LLM agent (Hermes) on my own machine. The problem was never the model — it was the interface . I had a Telegram tab open all day just to talk to it: type a command, wait, read a wall of text back, scroll. It felt like texting a very capable stranger. So I built Ghost Vessel — a monitor-resident, video-call-style avatar that fronts the agent. The name is the whole idea: the ghost is your agent, the vessel is the body it borrows. It's not a waifu toy; it's a real agent client that happens to have a face. Here's what actually turned out to be interesting to build. The reply is a script, not a string The core idea is an output contract . Instead of treating the agent's reply as text to print, I split every reply into three planes: dialogue → spoken via local TTS data → code, logs, files → rendered as chat cards, never read aloud action → emotion beats that drive the avatar Emotion beats are inline tags the model emits in-band with its answer: [working] — the avatar puts on glasses and takes notes while a task runs [confirm] deploy to prod? — pops a human-in-the-loop approve/cancel, and the agent blocks on your keypress [happy] / [concerned] / … — fine-grained facial expressions So "run the build, and if it passes, deploy" becomes a little performance : it looks busy while working, shows you the log as a card, then leans in and asks before the irreversible step. The text you'd have skim-read becomes something you glance at. No runtime GPU for the avatar The obvious way to animate a face is live inference. I didn't want that — the GPU is busy running the actual model. Instead the avatar is ~30 pre-rendered clips , and the emotion beats just select and blend between them (blink-aligned seamless idle loops, a head-pose "settle gate" so an expression only reveals when the head is frontal). The avatar's runtime cost is basically video playback. Your GPU stays 100% on your LLM. The tradeoff: no real-time lip-sync. I decided a believable talking mouth loop + expre

While researching API changes I noticed something — Google Maps removed DirectionsService on May 1 2026 with no soft fallback. Calls just throw runtime errors after the deadline. Most developers won't know until something breaks. So I built DepRadar — paste your package.json, it checks your exact stack against known deprecations and shows only the ones affecting you, with severity, sunset dates, and migration links. Currently tracks 13 real deprecations across: Google Maps (DirectionsService, DistanceMatrixService removed) OpenAI (Realtime API Beta sunset) AWS SDK v2 (maintenance mode) Microsoft Actionable Messages (retired) moment.js, request package And more Free → depradar.netlify.app Open source → github.com/Ahmed889-code/depradar What deprecations am I missing from your stack?

I've been coding with AI agents for about two years. Every major one. Cursor, Copilot, Codex, OpenCode. They're good at generating code. They all share one problem. They forget everything. You finish a session, close the window, and the agent resets. Next time you open it, you're starting from zero. "We use pnpm, not npm." "The database is SQLite, not Postgres." "Don't touch the migrations folder." You repeat yourself. Every. Single. Time. Some tools added memory features. Usually as an afterthought. A pinned file. A custom instruction. A context window that grows until it hits a wall and everything old gets silently dropped. I didn't want a bigger context window. I wanted an agent that accumulates knowledge the way a colleague does. Not by being retrained. By taking notes, writing down what it learned, and reading those notes next time. That's what Jean2 can do. Not through fine-tuning. Not through vector embeddings. Through files on disk that the agent reads and writes itself. But here's the thing: none of this is on by default. By default, Jean2 is as bare as Codex or OpenCode. A blank prompt. No memory. No skills. No session search. You opt in to each layer in workspace settings . That's the point. You build the agent you want, layer by layer. The Four Layers If you turn them on, Jean2's agent has four knowledge layers that persist across sessions. They're not features bolted on top. They're part of the system prompt that gets composed every time a session starts. 1. Workspace Memory Turn on workspace memory in workspace settings , and the workspace gets two files: MEMORY.md for shared knowledge and USER.md for your personal preferences within that workspace. Both live at <workspace>/.jean2/ . The concept is simple. Shared knowledge that's useful for any agent working in that workspace. "We use pnpm." "The database is SQLite." "Don't touch the migrations folder." Whatever agent you bring in, coding specialist, reviewer, docs writer, they all get the same context

OwO What's this? 💨✨ A tiny but mighty Mac mini M4 🍎⚡ with 16GB RAM, lots of local AI models 🤖🧠, and a BIG question… 🫣❓ -- an intro by Gemma 4. I have a Mac mini M4 with 16 GB of RAM, a pile of local models, and a very specific dream: Can I run a useful local AI agent that actually does things, but still feels nice to talk to? Not just "can it chat." Not just "can it write a haiku about Kubernetes." I mean: can it inspect the machine, patch files, search current information, use tools, avoid infinite loops, and still keep the cute assistant vibe? That last part turned out to matter more than I expected. My first round of testing was mostly about models. I compared gemma4:latest and ornith:9b inside OpenClaw, my local agent harness. Ornith won because it acted more like an agent. But after another day of testing, the story changed. The model still matters. Ornith is still the local model winner for me. But the harness matters just as much. And right now, my favorite setup is: Ornith + Hermes Agent The Original Question The original question was simple: Can a free local model behave like a useful agent on a small Mac? The machine is modest by AI workstation standards: Mac mini M4 16 GB RAM local model inference local agent harness Telegram or chat-style interface real files, real commands, real web/API checks This was never meant to be a scientific benchmark. No leaderboard. No synthetic score. No fake "reasoning" tasks. I tested practical things I actually care about: Find junk on disk and suggest what is safe to clean. Patch a Python script that fetches Bybit futures data. Search current web/API information and answer a crypto API question. My first conclusion was: Ornith beat Gemma. That is still true. But it was incomplete. The Thing I Missed: Gemma Had the Kawaii Soul ✨ I focused too much on tool use. That was fair, because agents need to act. But I missed something important: Gemma was much better at keeping the kawaii writing style ✨🌸. Gemma's messages were genu

Most agent demos are one-shot loops. You open a terminal, give the model a task, watch it call tools, and then the process dies. That is fine for coding sessions. It is a weak shape for an assistant that is meant to live in your actual workflow. Talon is built around the other shape: a persistent agent process with frontends, memory, tools, background jobs, and swappable model backends. What it runs on Talon can expose the same agent core through: Telegram Discord Microsoft Teams terminal chat a desktop/mobile companion bridge That means the agent is not tied to one UI. The chat app is just a mouth. The core state, tools, memory, goals, and model backend live behind it. Backends are swappable The same harness can run through: Claude Agent SDK OpenAI Agents Codex Kilo OpenCode Each backend implements the same capability interface, so the rest of the system does not need to care which model runtime is active. It has real operating machinery The important parts are not flashy. They are the things that let an agent keep working after the first message: MCP plugins for tools cron jobs for scheduled actions triggers for condition-based wakeups persistent goals for multi-session work long-term memory heartbeat mode for background progress dream mode for consolidation per-chat model and effort settings This is the difference between "chat with a model" and "run an assistant". Install npm install -g talon-agent talon setup talon start Repo: https://github.com/dylanneve1/talon If this is the kind of agent infrastructure you want more of, a GitHub star helps the project get found.

GitHub热门项目 | The best browser for both you and your AI agents work in parallel. | Stars: 479 | 199 stars this week | 语言: JavaScript

GitHub热门项目 | ⚡️ Streaming torrent client for the web | Stars: 31,207 | 225 stars this week | 语言: JavaScript

GitHub热门项目 | RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust. | Stars: 4,341 | 8 stars today | 语言: Rust

GitHub热门项目 | 🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia. | Stars: 11,682 | 15 stars today | 语言: TypeScript

GitHub热门项目 | Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it! | Stars: 20,866 | 24 stars today | 语言: TypeScript

GitHub热门项目 | Huly — All-in-One Project Management Platform (alternative to Linear, Jira, Slack, Notion, Motion) | Stars: 26,797 | 45 stars today | 语言: TypeScript

GitHub热门项目 | Univer is a full-stack framework for creating and editing spreadsheets / word processor / presentation on both web and server. | Stars: 13,695 | 160 stars today | 语言: TypeScript

GitHub热门项目 | This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities | Stars: 6,289 | 20 stars today | 语言: TypeScript

GitHub热门项目 | A high-performance, 100% client-side tool for removing Gemini AI image & video watermarks. Built with pure JavaScript using mathematically precise Reverse Alpha Blending. / 基于 JavaScript 的纯浏览器端 Gemini AI 图像和视频无损去水印工具，使用数学精确的反向 Alpha 混合算法 | Stars: 4,749 | 27 stars today | 语言: JavaScript

GitHub热门项目 | Sample Whatsapp App - Jasper's Market | Stars: 508 | 10 stars today | 语言: JavaScript

GitHub热门项目 | AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph. | Stars: 80,027 | 885 stars today | 语言: Python

GitHub热门项目 | | Stars: 2,604 | 14 stars today | 语言: Python

GitHub热门项目 | SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts. | Stars: 11,571 | 261 stars today | 语言: Python

GitHub热门项目 | 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h! | Stars: 52,981 | 176 stars today | 语言: Python