46,757 results for and

github.com
Show HN: Open-sourced AI Agent runtime (YAML-first)https://github.com/NikoSokratous/agentctlBeen running AI agents in production for a while and kept running into the same issues:controlling what they can do tracking costs debugging failures making it safe for real workloadsSo we built AgentRuntime, the infrastructure layer we wished we had. Not an agent framework, but the platform around agents:policies memory workflows observability cost tracking RAG governanceAgents and policies are defined in YAML, so it's infrastructure-as-code rather than a chatbot builder. Example – agents and policies in YAML agent.yaml – declarative agent config name: support_agentmodel: provider: anthropic name: claude-3-5-sonnetcontext_assembly: enabled: true embeddings: provider: openai model: text-embedding-3-small providers: - type: knowledge config: sources: ["./docs"] top_k: 3 policies/safety.yaml – governance as code name: security-policyrules: - id: block-file-deletion condition: tool.name == "file_delete" action: denyCLI – run and inspect Create and run an agent agentctl agent create resear
Mar 3, 2026 1:31 PM
news.ycombinator.com
Ask HN: How are you structuring Markdown-based context for AI coding agents?https://news.ycombinator.com/item?id=47231386I’ve recently transitioned from using LLMs in-browser to a local agentic workflow in VS Code (Gemini Code Assist). I can approve/disapprove changes which is nice, but I’ve hit a wall regarding context management. Initially, I provided all the whole repo as context to the non-agentic version of Gemini code assist and it performed well.I read the agentic mode is "better" so to keep the agent aligned with my project's architecture, I’ve manually built 7 dense Markdown files that serve as the system instructions for the project. I require Gemini to update these files as we implement features.gemini.md (instructs gemini to read the other md files and handle updating) project_overview.md, architecture.md, features.md, database.md, api.md, security.mdEach file is between 500–1,500 words so I’m concerned if f this is the right way to go. There seems to be no consensus on context file best practices. I’m seeing strong arguments for both minimalist, lean instructions and dense, project-wide spec
Mar 3, 2026 12:29 PM
bing.com
Best Teeth Whitening Kits 2026: 9 Dentist-Approved Pickshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8a3c1a38d4427896cd9a66bbedcadb&url=https%3A%2F%2Fwww.forbes.com%2Fsites%2Fforbes-personal-shopper%2Farticle%2Fbest-teeth-whitening-kit%2F&c=14368720991972801861&mkt=en-usIf you’re looking to brighten your smile, getting an at-home teeth whitening kit is convenient, effective and safe—as long as you choose dentist-approved formulas. As the deputy editor who oversees ...
Mar 3, 2026 12:09 PM
science.nasa.gov
Collaborating Through Data: Inside the PSI Users Grouphttps://science.nasa.gov/science-research/biological-physical-sciences/collaborating-through-data-inside-the-psi-users-group/About the PSI Users Group The Physical Sciences Informatics (PSI) Users Group is a recurring Webex forum that brings together researchers, open-science practitioners, and collaborators from across the physical sciences community. Designed to foster collaboration, knowledge-sharing, and data-driven discovery, each meeting provides participants with a platform to directly engage with leading researchers and PIs. Each […]
Mar 2, 2026 5:30 PM
bing.com
El gobierno de España niega a EE. UU. el uso de sus bases militares para el ataque a Iránhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a89035b023747f999f8951d7efdf657&url=https%3A%2F%2Fwww.nytimes.com%2Fes%2F2026%2F03%2F02%2Fespanol%2Fmundo%2Fespana-ejercito-trump.html&c=7459409063469076704&mkt=en-usLa nueva política es la crítica más reciente a Estados Unidos por parte de España, que ha destacado en Europa por su oposición constante al gobierno de Trump. Por Jason Horowitz Reportando desde ...
Mar 1, 2026 4:00 PM
news.ycombinator.com
Show HN: E8-Matrix: open-source physical particle discovery platformhttps://news.ycombinator.com/item?id=47206366I’d like to share E8-Matrix - a open-source physical particle discovery platform (recent program paper titled “From a High-Symmetry Sector to Testable Observables: An E8-Motivated Projection Program”) and would greatly appreciate any constructive feedback from the community.The work outlines a top‑down computational framework that connects a high‑symmetry ⊇ E8 structure to 3+1D observables via an operational projection Π.Instead of ad‑hoc effective shifts, the goal is to trace predictions back to explicit representation content and symmetry selection rules.- Proton decay: A spectrum‑driven “Track A” scan identifies a golden point configuration yielding τ_p ≈ 1.22×10⁴¹ years (for p → e⁺π⁰) while keeping the α₃ mismatch at the unification scale below 2.7% (1‑loop piecewise running). - Dark photon: The model predicts a light dark‑photon region m_A' ∼ 10⁻⁴–1 eV, ε ≳ 10⁻⁸, illustrated against an order‑of‑magnitude IAXO‑like reach. - Framework: The paper details the E8 → A7 × U(1)' → SU(5) →
Mar 1, 2026 1:07 PM
github.com
Show HN: I built a zero-browser, pure-JS typesetting engine for bit-perfect PDFshttps://github.com/cosmiciron/vmprintHi HN, I'm a film director by trade, and I prefer writing my stories in plain text rather than using clunky screenplay software. Standard markup like Fountain doesn't work for me because I write in mixed languages, so I use Markdown with a custom syntax I invented to resemble standard screenplay structures.This workflow is great until I need to actually generate an industry-standard screenplay PDF. I got tired of manually copying and pasting my text back into the clunky software just to export it, so I decided to write a script to automate the process. That's when I hit a wall.I tried using React-pdf and other high-level libraries, but they failed me on two fronts: true multilingual text shaping, and complex contextual pagination. Specifically, the strict screenplay requirement to automatically inject (MORE) at the bottom of a page and (CONT'D) at the top of the next page when a character's dialogue is split across a page break.You can't really do that elegantly when the layout engine
Mar 1, 2026 12:25 PM
news.ycombinator.com
Show HN: DevIndex – Ranking 50k GitHub developers using a static JSON filehttps://news.ycombinator.com/item?id=47193729Hey HN,I’ve always been frustrated by the lack of an accurate ranking for top open-source contributors on GitHub. The available lists either cap out early or are highly localized, completely missing developers with tens or hundreds of thousands of contributions.So, I built DevIndex to rank the top 50,000 most active developers globally based on their lifetime contributions.From an engineering perspective, the constraint I imposed was: *No backend API.* I wanted to host this entirely on GitHub Pages for free, meaning the browser had to handle all 50,000 data-rich records directly.Here is how we made it work:1. *The Autonomous Data Factory (Backend):* Because GitHub's API has no "Lifetime Contributions" endpoint, we built a Node.js pipeline running on GitHub Actions. It uses a "Network Walker" spider to traverse the social graph (to break out of algorithmic filter bubbles) and an Updater that chunks GraphQL queries to prevent 502 timeouts. The pipeline continuously updates a single `user
Feb 28, 2026 11:13 AM
news.google.com
Jr NTR Unveils Intense ‘Mrithunjay’ Trailer, Praises Sree Vishnu’s Upcoming Thrillerhttps://news.google.com/rss/articles/CBMirgFBVV95cUxPOGlhNkdWamxSdEtwdkhhOTNFelJjSXZVekFFVTlsMGRTdlg3c1VTdTY1NTh3UXRKYWhuZG8wbjktcmRZcnBxNURVUHAzbTN1QjNzNFhoV2ltQVYwZ0VjS1hxMG56SkpGd3Z5WWtndEhlY05nY0x2RVlxRG9DY2tWQUhaUGpQWUx3U1Bhd1YwUHdQX1FfdDhzb1ItaHFIZC1pa1ZCODNaRXpTbkQ2dWc?oc=5Jr NTR Unveils Intense ‘Mrithunjay’ Trailer, Praises Sree Vishnu’s Upcoming Thriller  INDIA New England News
Feb 28, 2026 8:00 AM
spaceflightnow.com
NASA announces major overhaul of Artemis moon program: “We’ve got to get back to basics”https://spaceflightnow.com/2026/02/27/nasa-announces-major-overhaul-of-artemis-moon-program/New NASA Administrator Jared Isaacman announced a major overhaul of the agency's Artemis moon program Friday, acknowledging that the agency's plan to land astronauts on the moon in 2028 was not realistic without another preparatory mission first to lay the groundwork.
Feb 27, 2026 5:31 PM
github.com
Show HN: Stash – AI-powered self-hosted bookmark managerhttps://github.com/ayoub9360/stash-bookmarkI built Stash, a self-hosted bookmark manager that uses AI to automatically process your links.Paste a URL and it fetches the content, parses it, summarizes it, auto-assigns categories and tags, and generates a vector embedding for search.Search is hybrid — it combines pgvector cosine similarity (semantic) with PostgreSQL tsvector (keyword) and merges both with Reciprocal Rank Fusion. You can search in natural language ("articles about distributed systems tradeoffs") or with simple keywords.It's single-tenant by design: one password, no user accounts, no tracking. Your data stays on your machine.The project is MIT licensed don't hesitate to contribute. Some areas where help would be great: browser extension, bookmark import/exportGitHub: https://github.com/ayoub9360/stashHappy to answer questions about the architecture or the hybrid search approach.
Feb 27, 2026 2:11 PM
esa.int
Navigation Training Course now open for applicationhttps://www.esa.int/Education/ESA_Academy/Navigation_Training_Course_now_open_for_application3ESA Academy is inviting university students to apply for the Navigation Training Course, taking place from 22 to 26 June 2026 at ESA Academy’s Training and Learning Facility in ESA ESEC, Belgium. Organized in collaboration with ESA Education and ESA’s Directorate of Navigation, this course is perfect for those curious about the future of satellite navigation
Feb 26, 2026 2:41 PM
github.com
Show HN: Context Harness – Local first context engine for AI toolshttps://github.com/parallax-labs/context-harnessContext Harness is a single Rust binary that gives AI tools like Cursor and Claude project-specific memory. It ingests docs, code, Jira tickets, Slack threads, and anything else into a local SQLite database, indexes them with FTS5 and optional vector embeddings, and exposes hybrid search via CLI and an MCP-compatible HTTP server.I built this because I kept hitting the same problem: AI tools are powerful but have no memory of my complex multi-repo project. They can't search our internal docs, past incidents, or architecture decisions. Cloud RAG services exist, but they're complex, expensive, and your data leaves your machine. I wanted something I could point at my sources and just run `ctx sync all`.Quick start: # Install (pre-built binaries available for macOS/Linux/Windows) cargo install --git https://github.com/parallax-labs/context-harness.git # Create config and initialize ctx init # Sync your data sources (filesystem, Git, S3, or Lua scripts) ctx sync all # Search from CLI ctx sea
Feb 26, 2026 6:26 AM
science.nasa.gov
NASA’s Webb Examines Cranium Nebulahttps://science.nasa.gov/missions/webb/nasas-webb-examines-cranium-nebula/Two heads are better than one in the latest images from NASA’s James Webb Space Telescope, which reveal new detail in a mysterious, little-studied nebula surrounding a dying star. Nebula PMR 1 is a cloud of gas and dust that bears an uncanny resemblance to a brain in a transparent skull, inspiring its nickname, the […]
Feb 25, 2026 3:00 PM
europeanspaceflight.com
Eutelsat to Raise €1.5 Billion to Refinance its Debthttps://europeanspaceflight.com/eutelsat-to-raise-e1-5-billion-to-refinance-its-debt/European satellite operator Eutelsat has announced that it will raise €1.5 billion to refinance existing debt and add cash to the company’s balance sheet. In June 2025, Eutelsat reported net debt of just over €2.6 billion, up €82.2 million year-on-year, with a net debt-to-EBITDA (Earnings Before Interest, Taxes, Depreciation, and Amortisation) ratio of 3.88×. At […] The post Eutelsat to Raise €1.5 Billion to Refinance its Debt appeared first on European Spaceflight.
Feb 25, 2026 10:34 AM
spacedaily.com
Brain learns faster from rare rewards than from repetitionhttps://www.spacedaily.com/reports/Brain_learns_faster_from_rare_rewards_than_from_repetition_999.htmlLos Angeles CA (SPX) Feb 20, 2026 More than a century after Pavlov trained dogs to link a bell with food, neuroscientists at the University of California, San Francisco report that the brain may rely more on the timing of rewards than on sheer repetition when forming associative memories of cues and outcomes. Their work suggests that what matters for learning is how far apart cue-reward experiences are spaced in time, rather tha
Feb 25, 2026 10:14 AM
news.google.com
Governor Announces Historic Tax Relief as Louisiana Families Save Morehttps://news.google.com/rss/articles/CBMiowFBVV95cUxQc3RidTFRUTQ0eHFjbkVMLWxCdnhKU2VoMmNhN3JpQk1VYkRhcllxejNIVjFRSFNfcmdwX2tSMzg3SUFYZTRTdHVqck1sLUJKT1gxeEEzbldPRTI5TDlhR2xfUEtvTzJJUXoxd2loVk12eGhMVW15dTRUMUhfUk15SDVXOVl6Vmd5b3lEcjBFcTczVWRrZ3gtWVhiSHhNNS0wc3Rj?oc=5Governor Announces Historic Tax Relief as Louisiana Families Save More  Office of Governor Jeff Landry (.gov)
Feb 25, 2026 8:00 AM
news.ycombinator.com
Seedream 5.0 Lite API Pricing Breakdownhttps://news.ycombinator.com/item?id=47146196Seedream 5.0 Lite just dropped. Seedream 5.0 Lite just dropped. If you're curious about the most cost-effective way to run this in a production workflow, I put together a quick breakdown of the features and a price comparison across a few providers.1. Seedream 5.0 Lite Key Enhancements Here is what stands out in the 5.0 Lite update: - Stronger Feature Consistency: Noticeable jump in facial consistency and detail when using multi-image references. - Detail Preservation: It maintains natural skin tones and postures much better across batch outputs. - Precise Instruction Following: Handles complex camera angles and specific brush-style effects more reliably. - Multimodal Reasoning: You can feed it rough sketches or abstract logic, and it translates them into commercial-ready designs. - Visualizing Complex Data: Great for turning raw data or knowledge sets into clean visuals for presentations. - Broad Use Cases: Fast enough for marketing/E-commerce but high-quality enough for film/game pre
Feb 25, 2026 1:39 AM
bing.com
USA TODAY Carshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a894ef46410415cbb6f3695266a2192&url=https%3A%2F%2Fwww.usatoday.com%2Fcars&c=12182142523958114480&mkt=en-usExplore the latest in cars, from news to reviews, shopping tips, and tech trends shaping the automotive world.
Feb 25, 2026 12:08 AM