标签：#ens

GitHub热门项目 | A list of developer portfolios for your inspiration | Stars: 23,158 | 53 stars today | 语言: Python

GitHub热门项目 | Memory engine and app that is extremely fast, scalable. The Memory API for the AI era. | Stars: 23,064 | 236 stars today | 语言: TypeScript

GitHub热门项目 | A straightforward method for training your LLM, from downloading data to generating text. | Stars: 2,577 | 327 stars today | 语言: Jupyter Notebook

GitHub热门项目 | The open-source repo for docs.github.com | Stars: 19,599 | 20 stars today | 语言: TypeScript

GitHub热门项目 | Hermes WebUI: The best way to use Hermes Agent from the web or from your phone! | Stars: 9,591 | 320 stars today | 语言: Python

GitHub热门项目 | 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! | Stars: 56,093 | 639 stars today | 语言: Python

GitHub - nikhilt101/email-blast-tool: Open source HTML email sender tool using CSV/XLSX + Gmail SMTP · GitHub Open source HTML email sender tool using CSV/XLSX + Gmail SMTP - nikhilt101/email-blast-tool github.com

This is a submission for the Hermes Agent Challenge : Write About Hermes Agent Most AI agents have a dirty secret: they forget everything the moment the session ends. You explain your project once. Then again next time. And again. The agent never gets better at your workflow — it just stays a general-purpose tool that happens to be smart. Hermes Agent is built differently. It ships with two systems that together form something closer to a genuine long-term memory: a Skills System and a Persistent Memory layer. This post digs into how they actually work — not the marketing summary, but the mechanics. The Problem With Stateless Agents Before getting into Hermes, it's worth understanding what problem this solves. Standard LLM-based agents operate inside a context window. Everything the agent knows during a session lives in that window. When the session ends, it's gone. The next time you open a conversation, you're talking to an agent with no memory of you, your codebase, your preferences, or the workflows you've developed together. Some tools patch this with naive "memory" — they dump a text blob of past conversations into the system prompt. This works up to a point, but it's not selective, it gets expensive as context grows, and it doesn't help the agent get better at tasks — just recall facts. Hermes takes a different approach with two distinct systems serving different purposes. System 1: The Skills System (Procedural Memory) Skills in Hermes aren't plugins you install. They're on-demand knowledge documents — markdown files the agent loads when it needs them, and more importantly, creates on its own when it discovers something worth remembering. The SKILL.md Format Every skill is a structured markdown file with a YAML frontmatter header: --- name : deploy-runbook description : Our deployment runbook — services, rollback, Slack channels version : 1.0.0 metadata : hermes : tags : [ deployment , runbook , internal ] requires_toolsets : [ terminal ] --- # Deploy Runbook

How RAGScope Knows Which Chunks Your LLM Actually Used Your retriever fetched 10 chunks. Your LLM only used 3. RAGScope shows a precision score of 30 out of 100. The question every new user asks: how does it know? There is no OpenTelemetry attribute that says "this chunk was in the context window." RAGScope infers it — and the way it does this is the most consequential piece of engineering in the whole tool. There Is No "In Context" Attribute in OTel The OpenTelemetry semantic conventions for generative AI ( gen_ai.* ) define attributes for model, input/output tokens, and retrieved documents. They do not define anything like gen_ai.chunk.reached_llm or gen_ai.retrieval.used_document_ids . When your RETRIEVER span fires, you get a list of documents. When your LLM span fires, you get a prompt and a completion. The two spans are connected by a parent-child trace relationship — but there is no attribute that maps which retrieved documents appear in which prompt. This gap matters. A reranker might drop 7 of your 10 chunks. Your application code might apply a token budget and truncate 4 more. From the trace alone, you cannot tell. RAGScope needs this information to compute the precision sub-score — the highest-weighted metric at 40% of the overall score. Getting it wrong would make precision meaningless. The Substring Match — How assembleContext Works RAGScope's answer is in src/enrichment/pipeline.ts , in a function called assembleContext : function assembleContext ( chunks : RagChunk [], llmSpans : ParsedSpan []): RagChunk [] { const llmPrompts = llmSpans . map (( s ) => s . prompt ). filter (( p ): p is string => !! p ); if ( llmPrompts . length === 0 ) return chunks ; let position = 0 ; return chunks . map (( chunk ) => { if ( ! chunk . content ) return chunk ; const inContext = llmPrompts . some (( p ) => p . includes ( chunk . content ! )); if ( inContext ) { return { ... chunk , inContext : true , contextPosition : position ++ }; } return { ... chunk , inContext :

Most apps don't just call one API endpoint. They call a whole chain of them. For example, you might log in, get a token, and then pass that token to another service. Tracking these multi-step chains can get messy quickly. To help fix this, the OpenAPI Initiative created the Arazzo Specification . It gives us a standard way to link different endpoints into clear workflows. But writing these workflow files by hand in a regular text editor is tough. It is very easy to lose track of how data moves from one step to the next. That is why I built Arazzo Visualizer for VS Code. It is a free, open-source extension that makes the Arazzo spec visual and easy to use. Live Interactive Graphs The extension reads your workflow files and turns them into interactive maps on the fly. See Data Flow: Look at exactly how data moves between steps. Catch Errors Early: Spot broken paths before you even run your code. Clean Layouts: Navigate large workflows without getting lost in thousands of lines of text. Built-In Workflow Runner Seeing the map is great, but testing it is even better. The tool has a step-by-step runner built right into your editor. Run a single step or execute the whole chain. See real-time data payloads and HTTP headers. Watch requests happen live to pinpoint bugs fast. Give it a Try The project is fully open source, and you can grab it or check out the code using the links below: Download: Install it directly from the VS Code Marketplace . Source Code: Check out the repository, report bugs, or contribute on GitHub . Deep Dive: Read my full technical breakdown and design on Medium . If you are working with API chains, I would love for you to try it out. Drop your feedback in the comments below! Note: Arazzo v1.1.0 is out with official AsyncAPI support. I am currently updating the VS Code extension to support these new features. Stay tuned for future updates!

You've seen this before. You ask your AI agent: "Find ∫ x·e^x dx" It confidently replies: e^x + C , complete with a plausible-looking derivation. You nod. Then you check — the correct answer is (x−1)·e^x + C . It was wrong by a mile, and you almost shipped it. This is the fundamental problem with AI math today: LLMs can talk, but they can't verify their own work. They sound convincing while being catastrophically wrong. And the more complex the problem, the better the hallucination. Math.skill changes that. It's an open-source mathematical reasoning skill for AI agents — install it, and your agent stops guessing and starts verifying. What Makes It Different Typical AI Math Plugin Math.skill Workflow Prompt → LLM → answer Prompt → 7-step pipeline → ≥2 verifications → answer Verification None Answer blocked if verification fails Open problems Might hallucinate a "solution" Honestly says "this is unsolved" Error recovery No mechanism Auto-backtrack, fix, recompute, re-verify The core differentiator: a verification engine that runs at least 2 of 11 independent checks on every answer. No answer leaves the pipeline unverified. Period. The 7-Step Pipeline Every problem flows through this: Step What Happens Why It Matters 1. Parse Extract conditions, goals, variables, implicit domain constraints Catches misread problems before they waste your time 2. Model Build formal representation: equation, function, matrix, probability space, etc. Prevents building the wrong mathematical structure 3. Select Choose the optimal method from 30+ strategies Avoids brute-forcing when elegance exists 4. Solve Step-by-step with mathematical justification at every transformation Full traceability — nothing hidden 5. Verify Apply ≥2 of 11 independent verification methods The differentiator — catches what LLMs miss 6. Correct If verification fails: backtrack to last known-good step, fix, recompute, re-verify No "doubling down" on wrong answers 7. Deliver Exact answer (not approximate), domain con

I Built pretext-pdf: Serverless PDFs Without Chromium I got frustrated with PDF generation in Node.js. Every tool had trade-offs, and none of them felt right. The Problem Every time I needed to generate PDFs programmatically, I hit the same walls: Puppeteer — Renders HTML to PDF beautifully, but takes 500ms-2s per page. Way too slow for batch operations. wkhtmltopdf — Old, fragile, breaks in production, dependency hell. pdfmake — Good for simple invoices, falls apart with complex layouts. All of them — Overkill if you're not rendering HTML. And here's the kicker: I didn't need to render HTML. I had structured data (invoices, reports, certificates) that I needed to turn into PDFs programmatically . The Solution I built pretext-pdf — a JSON-based PDF generation library. Instead of: javascript // ❌ Puppeteer: render HTML const browser = await puppeteer.launch(); const page = await browser.newPage(); await page.setContent(html); const pdf = await page.pdf(); // 1000ms+ You do: // ✅ pretext-pdf: define structure const doc = { sections: [ { type: 'heading', text: 'Invoice' }, { type: 'table', rows: [...] } ] }; const pdf = await renderPDF(doc); // 40-100ms No Chromium. No external dependencies. Pure Node.js. Why This Matters If you're building: ✅ Invoice generation systems ✅ Dynamic reports for your SaaS ✅ AI agents that create PDFs (Claude, Cursor, Windsurf) ✅ Certificate systems ✅ Multi-language documents ...pretext-pdf is built for you. Today: v2.0.14 Launch I just shipped a major upgrade. The text layout engine (which handles how words break across lines) is now significantly better: Better CJK + Latin mixed-script handling Smarter punctuation (quotes stay with their text) 7-12% faster Zero breaking changes The Stats 337 tests passing — production-ready 0 critical vulnerabilities — secure MIT licensed — free to use Open source — contribute or fork Technical Foundation The layout engine is based on pretext by Cheng Lou (React core team). I cherry-picked 11 patches for

Most agent frameworks assume one agent, one app, one bill. The moment you run agents for many clients, two problems appear that no runtime solves for you: you can't prove which client burned which tokens , and nothing stops one client's workspace from leaking into another's . I built Octorato to fix exactly that. What Octorato is Octorato is an open-source AI agent operating system: one file-native "brain" — rules, 190+ skills, 180+ specialist agents, all plain markdown under git — that a single operator runs across many sealed client "arms," with per-client token attribution and opt-in budget caps. It's not a runtime you import. It's the agent's self as files you can read, diff, fork, and own — runtime-agnostic (it runs on Claude Code today). The octopus model One brain , many arms . The brain holds the shared self: rules (the constitution), skills (HOW to do things), agents (WHO does them). Each arm is a sealed deployment serving exactly one client. Knowledge flows down (generic skills cascade to every arm) and lessons flow up (anonymized patterns get distilled back into the brain). Like a real octopus, most of the neurons live in the arms, not the head. Why "file-native" matters Your agent's identity, skills, and memory normally live trapped inside vendor code and a cloud console — you can't read the whole self, diff a change, or move it. Octorato keeps all of it as plain markdown under version control. Identity becomes diffable, reviewable, portable, and ownable . Text outlives runtimes. The part nobody else does: FinOps and isolation are the same wall Because each arm is a sealed cell that no other arm can see, every token an arm spends is attributable to exactly one client by construction. Cellular isolation is per-client FinOps — the wall that seals a client is the wall that meters it. Concretely: per-arm USD rollup (estimated from local session logs at list price), cost-spike alerts, and an opt-in PreToolUse budget gate — wire the hook and set a client's cap

Hi! I want to share a project that I work for a while. It started from idea to get rid off manual copying data from game design documents to game engine. Here you can define your game objects, their props, relations and everything will be stored in structural JSON format that can be read by Unity, Godot, Unreal and other engines. What we have now? construct **wiki-like documents **using a block editor and template system (markdown is supported too) design dialogues of your game in special graph editor create maps and prototype levels on canvas store and manage database of game objects use created objects inside engine directly or export data to customizable data formats (arbitrary JSON, CSV) Made it free and open source. Please try (have Windows and Mac builds) and give your feedback Source code: https://github.com/ImStocker/ims-creators Itch.io: https://nordth.itch.io/imsc-desktop

Large language models are good at sounding structured. That is not the same as being structured. Ask an AI assistant to "use first principles" and it may produce a confident answer with the phrase "first principles" near the top. Ask it to "red-team this plan" and it may list generic risks. Ask it to "apply OODA" and it may give you four headings without doing the hard part: orienting against assumptions, constraints, and evidence. That failure mode is subtle because the answer looks responsible. It has the right vocabulary. It has the right shape. But the method did not actually control the analysis. I built methodology-toolkit to target that gap. The goal is not to add more clever prompts to Claude Code. The goal is to add a small layer of discipline around non-trivial decisions: classify the problem, choose methods that fit, apply those methods explicitly, verify load-bearing claims, and stress-test plans before they harden into action. Repository: https://github.com/gagharutyunyan1993/methodology-toolkit The Problem: Methodology Theater Methodologies are useful because they constrain attention. First Principles asks you to strip assumptions and rebuild from base facts. ACH asks you to compare competing hypotheses by disconfirming evidence, not by collecting confirmations for your favorite answer. OODA asks you to separate raw observation from orientation, where bias and context do most of the work. Pre-mortem asks you to imagine the plan has already failed so optimism does not screen out obvious risks. When an AI assistant merely names those methods, you get the cost without the benefit. The answer becomes longer, more formal, and more convincing, but not necessarily more correct. That is worse than a short intuitive answer because the structure creates false confidence. methodology-toolkit treats that as the core anti-pattern: If a method is named, its steps must be walked. Not hinted at. Not summarized. Applied. Methodology theater: right vocabulary, no method

c_std: A Leak-Free, Cross-Platform Standard Library for Modern C Bringing the comfort of the C++ STL and Python's standard library to C17 — without leaving C A technical white paper. Executive summary C is still the substrate of the computing world — kernels, databases, language runtimes, embedded firmware, and the inner loops of nearly everything else. Yet the moment you step away from the kernel and try to write ordinary application code in C, you feel the gap: no growable vector, no hash map, no JSON parser, no string type that doesn't invite a buffer overflow. You either pull in a grab-bag of mismatched third-party libraries, each with its own conventions and failure modes, or you re-implement the same dynamic array for the hundredth time. c_std is an attempt to close that gap deliberately and coherently. It is a single, consistent library — written in pure C17 — that reimplements a large slice of the C++ Standard Library (containers, algorithms, smart pointers) alongside many Python-style conveniences ( json , regex , random , statistics , csv , config , even turtle graphics). It targets Windows and Linux from one source tree, compiles cleanly under -Wall -Wextra , and — this is the part I care about most — is verified leak-free under Valgrind , module by module, example by example. This paper explains the design philosophy, the architecture, and the engineering discipline that makes a library like this trustworthy enough to build on. 1. The problem: C's missing middle Every C programmer knows the two extremes. At the bottom, the language itself: pointers, malloc , memcpy , raw arrays. At the top, whatever the platform hands you — <windows.h> or POSIX, OpenSSL, a JSON library someone wrapped a decade ago. The middle — the layer the C++ STL and Python's batteries-included standard library occupy — is missing. That missing middle has a real cost. It shows up as: Re-invention. Teams write their own vector, their own string builder, their own linked list, each subt

GitHub热门项目 | 使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.) | Stars: 11,496 | 44 stars this week | 语言: JavaScript

GitHub热门项目 | Skills Catalog for Codex | Stars: 20,894 | 975 stars this week | 语言: Python

GitHub热门项目 | A Kiro Client in Rust | Stars: 1,560 | 5 stars today | 语言: Rust

GitHub热门项目 | 💥 Blazing fast terminal file manager written in Rust, based on async I/O. | Stars: 38,839 | 74 stars today | 语言: Rust