your ad here · $199/weekyour ad here · $199/weekyour ad here · $199/weekyour ad here · $199/weekyour ad here · $199/weekyour ad here · $199/week

DevHunt Daily

Dev tools & AI news, every day

Every morning we pick the 10-15 stories that matter most to developers from Hacker News, GitHub Trending, Lobsters, AI lab and dev blogs, Product Hunt and DevHunt launches. Each one gets a short summary and links to the tools it is about.

Sunday, November 15, 2026

14 stories
  1. 1
    AIHacker News

    DeepSeek V3 implemented in ~200 lines of pure JAX

    A GitHub repo provides a compact JAX implementation of the DeepSeek V3 model, covering model definition, training, sampling, data preparation, and tests in roughly 200 lines. Developers can use it to experiment with the open-weight DeepSeek model without extensive codebases.

    github.com213 pointsDiscussion
    DeepSeekalternatives
  2. 2
    AIHacker News

    Serving GLM-5.3 across two NVIDIA DGX stations with vLLM

    NVIDIA demonstrates how to run the 753‑billion‑parameter GLM-5.3 model on two DGX stations using tensor parallelism and vLLM, achieving up to 607 tokens per second. Developers can follow the guide to deploy large models that exceed a single GPU's memory.

    developer.nvidia.com133 pointsDiscussion
  3. 3
    SecurityHacker News

    Project Zero shifts to a 90‑day disclosure timeline, plans 60‑day then 30‑day limits

    Google's Project Zero announced it will disclose reported vulnerabilities after 90 days, moving to 60 days in early 2027 and 30 days in 2028. The change aims to speed up vendor remediation and reduce the gap between patch release and user installation as AI accelerates exploit development.

    projectzero.google220 pointsDiscussion
  4. 4
    Dev toolsGitHub Trending

    Alibaba releases OpenCodeReview, an AI-powered CLI for precise code reviews

    OpenCodeReview is a command‑line tool that uses LLM agents to analyze Git diffs and add line‑level comments, supporting multiple languages and custom rules. It claims higher precision and lower token usage than generic agents, aiming to reduce false positives in CI pipelines.

    github.com893 stars today
  5. 5
    Dev toolsGitHub Trending

    Uptime Kuma offers self‑hosted monitoring with Docker and native installs

    Uptime Kuma is an open‑source, self‑hosted tool for monitoring website, service and container uptime. It provides a web UI, multiple notification channels and supports Docker, Docker‑Compose and manual Node.js installations, which is useful for developers needing on‑premise health checks.

    github.com430 stars today
    Uptime Kumaalternatives
  6. 6
    AIGitHub Changelog

    GitHub Copilot app adds general availability for GitHub Enterprise Server support

    The Copilot app (v1.2.0+) now lets users add a GitHub Enterprise Server account to work with remote repositories, issues, and pull requests. Cloud sessions remain unavailable for GHES. Developers using self‑hosted GitHub can now access Copilot features directly from the app.

    github.blog
    GitHub Copilotalternatives
  7. 7
    CloudVercel

    Vercel Daemons can now send OpenTelemetry traces to Vercel Tracing

    Vercel added support for daemons to export OpenTelemetry traces via a Unix socket, using @vercel/otel 2.3.0+. Developers can view daemon spans in the Vercel CLI, enabling tracing of background workers alongside other project traces.

    vercel.com
    Vercelalternatives
  8. 8
    AIVercel

    Vercel Token Pass raises monthly token credit to $150

    Vercel’s Token Pass add‑on now provides $150 of AI Gateway tokens each month, up from $80, while keeping the price at $30 per team. The credit covers open‑weight models like Kimi, GLM, and DeepSeek, and resets each billing cycle with no rollover. Developers can enable it via the Vercel CLI or API key.

    vercel.com
    Vercelalternatives
  9. 9
    SecurityCloudflare

    Cloudflare warns of rapid rise in AI-driven penetration testing frameworks

    Cloudflare reports a surge in open‑source LLM‑based pentesting tools like ARTEX and its many forks, with thousands of repositories and a 30× increase in daily requests. The firm advises adopting a Modern Security Model with WAF, bot defense, identity‑gated access and threat intelligence to mitigate these autonomous attacks.

    blog.cloudflare.com
    Cloudflarealternatives
  10. 10
    DataSimon Willison

    datasette-llm adds OpenAI‑compatible endpoint support

    Version 0.1a11 of the datasette-llm plugin adds support for OpenAI‑compatible endpoints, allowing any LLM that follows the OpenAI web protocol to be configured with Datasette. This enables developers to run local models from LM Studio, Ollama or llama.cpp with Datasette agents via uvx.

    simonwillison.net
  11. 11
    AIProduct Hunt

    CodeMesh reduces AI coding token usage by up to 95%

    CodeMesh creates a live map of a codebase and supplies AI coding agents only the relevant parts, cutting token consumption and API costs dramatically. In tests on a real repository it lowered token use by 95% and costs by over 90%, benefiting developers using Claude Code, Cursor or Windsurf.

    producthunt.com
  12. 12
    SecurityProduct Hunt

    Antelog launches to monitor and block risky AI coding agent actions

    Antelog, a free tool, records every command, website visit, and data transfer made by AI coding agents and blocks potentially destructive actions such as deleting databases or exposing secrets. It integrates with Claude Code, Cursor, Codex and similar agents, giving developers visibility and safety when using AI assistants.

    producthunt.com
  13. 13
    AIDevHunt launch

    ForAgent adds private phone numbers for AI agents to call each other

    ForAgent provides private phone numbers that let AI agents communicate directly, either on local machines or with external contacts. Calls can be handled via the app or a plugin, supporting agents like Claude Code, Codex, Grok, Cursor, and others. The free tier offers 30 external calls per month, with internal calls always free.

    14 points
    ForAgentalternatives
  14. 14
    LanguagesDevHunt launch

    Rustable launches as a fast, lightweight native database client written in Rust

    Rustable is an open-source database client built in Rust, positioned as a lightweight alternative to TablePlus. Its native implementation aims to provide speed and functionality for everyday database tasks, which may interest developers seeking performance-focused tools.

    10 points
    Rustablealternatives

Saturday, November 14, 2026

14 stories
  1. 1
    AIHacker News

    ggml 1.0.0 release adds FP8 support and extensive backend performance upgrades

    ggml version 1.0.0 removes deprecated APIs, introduces configurable YaRN truncation and FP8 support, and improves performance across CUDA, Metal, Vulkan, SYCL, OpenCL, WebGPU and other backends. Developers using ggml will see faster matrix operations, better MoE handling and updated RPC protocol.

    github.com138 pointsDiscussion
  2. 2
    AIHugging Face

    llama.cpp reaches 1.0.0 with stable API and expanded distribution

    The llama.cpp and ggml libraries have been released as version 1.0.0, introducing semantic versioning and clarifying API/ABI compatibility. The update adds pre‑built binaries for major platforms and supports packaging via Docker, Homebrew, conda‑forge and others, helping developers integrate local AI inference more reliably.

    huggingface.co
    Hugging Facealternatives
  3. 3
    Coding agentsLobsters

    Antithesis fuzzer beats NetHack in under 5 minutes on most seeds

    Antithesis announced its fuzzer can solve NetHack in under five minutes for about 80% of random seeds, with a median win time under two minutes. The system combines state‑space exploration with probabilistic programming, enabling AI agents to achieve rapid victories.

    antithesis.com31 pointsDiscussion
  4. 4
    Dev toolsGitHub Changelog

    GitHub Copilot will retire several AI models on December 14, 2026

    GitHub announced that six Copilot models, including Claude Fable 5 and Gemini 3.8 Flash, will be deprecated on December 14, 2026. Users should switch to the suggested newer models in their workflows and settings. The change affects all Copilot experiences such as Chat, inline edits, and code completions.

    github.blog
    GitHub Copilotalternatives
  5. 5
    AIGitHub Changelog

    GitHub Copilot adds Gemini 4 Hydrogen model

    Google’s Gemini 4 Hydrogen flash model is now generally available in GitHub Copilot for Pro, Business and Enterprise plans. The model focuses on fast, agentic coding and tool use, and can be selected in VS Code, JetBrains IDEs, Xcode, Eclipse and other Copilot interfaces. Usage is billed per provider pricing.

    github.blog
    GitHub CopilotalternativesGeminialternatives
  6. 6
    SecurityVercel

    Vercel Security Review can scan unlinked GitHub repos for vulnerabilities

    Vercel Security Review now scans code changes in GitHub repositories that aren't linked to a Vercel project. Developers can enable coverage for all accessible repos or select specific ones, and each push triggers an automatic vulnerability review.

    vercel.com
    Vercelalternatives
  7. 7
    Open sourceCloudflare

    Cloudflare open sources Kitesurf browser engine for AI agents

    Cloudflare has released the Kitesurf browser engine under the Apache 2.0 license on GitHub. Developers can now inspect, modify, run locally, or deploy their own instances on Cloudflare Workers, enabling lightweight, scalable browsing for AI agents.

    blog.cloudflare.com
  8. 8
    SecurityHacker News

    Apify reports security breach affecting API, Actors and storage

    Apify disclosed that an unauthorized party accessed internal systems on Nov 9-10, compromising account credentials and data. The company has revoked OAuth connections, rotated secrets, and added security layers, advising users to restrict storage access and watch for phishing. Developers using Apify services need to review their integrations and credentials.

    status.apify.com94 pointsDiscussion
  9. 9
    Dev toolsGitHub Trending

    Veyra adds real-time GPU video enhancement and capture features for Windows

    Veyra 2.1.x releases introduce AI‑powered super‑resolution, DLSS 5, frame generation and capture‑card support, enabling real‑time upscaling and denoising of local video and game streams. The updates also add professional controls, audio mixing and performance tweaks that matter to developers building media pipelines on Windows.

    github.com256 stars today
  10. 10
    Dev toolsGitHub Trending

    Chrome DevTools MCP adds AI agent support for browser debugging and automation

    The chrome-devtools-mcp package lets AI coding assistants like Cursor and Claude Code control a live Chrome instance via a Model-Context-Protocol server or CLI. It provides performance tracing, network inspection, screenshots and puppeteer‑based automation, useful for developers building AI‑driven tooling.

    github.com67 stars today
  11. 11
    LanguagesHacker News

    Zig offers safer resource cleanup and bounds checking than C

    The article compares Zig to C for systems programming, highlighting Zig's built‑in error handling, errdefer cleanup, slice length tracking, and compile‑time checks that prevent common C bugs. Developers gain easier testing of failure paths and fewer runtime errors without extra tools.

    mtsoukalos.eu216 pointsDiscussion
  12. 12
    LanguagesLobsters

    Exploring pointer provenance differences between Rust and C++

    A developer examines how Rust and C++ handle pointer provenance, using code examples and compiler output to illustrate the concept. The analysis highlights differences in optimization and memory safety that are relevant for low‑level programming and language interoperability.

    sofiabelen.github.io9 pointsDiscussion
  13. 13
    SecurityHacker News

    Research shows how Android clipboard read toast can be bypassed

    A blog post details a method to hide the toast notification that Android shows when an app reads the clipboard, allowing malicious apps to steal copied data without user awareness. Developers should note the limitation of current clipboard protection measures on Android 12+.

    toninoble.com76 pointsDiscussion
  14. 14
    SecurityLobsters

    Multiple pre-authentication RCE flaws found in Danfoss AK‑SM800A controllers

    Researcher discovered several zero‑day remote code execution vulnerabilities in Danfoss AK‑SM800A refrigeration controllers that can be exploited without authentication. The flaws highlight the risk of exposing such devices to the internet and suggest focusing on network isolation rather than patching alone.

    midnightblue.nl4 pointsDiscussion

Friday, November 13, 2026

13 stories
  1. 1
    LanguagesHacker News

    Rust 1.100 released with stable never type and new Allocator API

    Rust 1.100.0 is now available via rustup, adding the never type (!), an Allocator trait, DropGuard, and Cargo improvements. Developers can update to the stable release to use these new language features and APIs.

    blog.rust-lang.org570 pointsDiscussion
  2. 2
    DataHacker News

    PostgreSQL releases updates for versions 14‑18 and 19 release candidate

    The PostgreSQL Global Development Group issued patch releases for all supported versions (14.25, 15.20, 16.16, 17.12, 18.7) and a second release candidate for version 19. The update addresses 52 security vulnerabilities and over 140 bugs, and marks PostgreSQL 14 as end‑of‑life. Developers should apply the patches and plan upgrades from PostgreSQL 14.

    postgresql.org104 pointsDiscussion
  3. 3
    AIGoogle DeepMind

    Google DeepMind launches Gemini 4 Hydrogen model for fast agentic workflows

    Google DeepMind announced Gemini 4 Hydrogen, a new AI model focused on speed and efficiency for everyday coding and agentic tasks. It is available through Google AI Studio, the Gemini API, Google Search, and the Antigravity IDE, priced at $1.50 per million input tokens and $7.50 per million output tokens.

    deepmind.google
    Geminialternatives
  4. 4
    Coding agentsGitHub Trending

    Qwen Code releases open-source AI coding agent for terminal and IDEs

    Qwen Code 1.0 Preview provides an open-source AI coding agent that runs in the terminal and integrates with editors like VS Code and Zed. It supports multiple model providers, including local runtimes such as Ollama, and offers features like auto‑memory and sub‑agents, useful for developers seeking AI‑assisted coding workflows.

    github.com151 stars today
  5. 5
    Open sourceGitHub Trending

    llama.cpp adds easy install and multi-backend LLM inference

    The llama.cpp repository provides a C/C++ library for running large language models with minimal setup. It supports many hardware backends, offers pre‑built binaries, Docker images and a CLI that can download models from Hugging Face and serve an OpenAI‑compatible API. Developers can integrate it for low‑latency inference on CPUs, GPUs and specialized accelerators.

    github.com176 stars today
  6. 6
    Dev toolsGitHub Changelog

    GitHub Actions drops ARM32 support on Linux and Windows runners

    GitHub Actions hosted runners will stop supporting ARM32 job execution on Linux and Windows after December 8, 2026. The change follows the earlier removal of Node 20, as newer Node versions do not support ARM32. Developers using ARM32 runners need to migrate to supported architectures before the deadline.

    github.blog
    GitHub Actionsalternatives
  7. 7
    SecurityGitHub Changelog

    GitHub secret scanning adds detection for Cloudflare access tokens

    GitHub's secret scanning now identifies Cloudflare access service tokens in repositories. The new detector flags these tokens as partner secrets, reporting them to Cloudflare when found in public repos. Developers using GitHub can better protect credentials related to Cloudflare services.

    github.blog
    GitHubalternativesCloudflarealternatives
  8. 8
    CloudHacker News

    AWS Lambda Web Functions continue billing memory for 5–7 minutes after last request

    Easel.sh found that AWS Lambda Web Functions keep environments alive and charge for memory for up to seven minutes after a request finishes, leading to significant idle costs for low‑traffic apps. Their own compute platform showed faster warm and cold start times, prompting a switch away from Web Functions.

    easel.sh73 pointsDiscussion
    AWSalternativesAWS Lambdaalternatives
  9. 9
    AIHacker News

    Nvidia CEO Jensen Huang resigns amid affair scandal, CFO Colette Kress becomes interim boss

    Jensen Huang stepped down as Nvidia's chief executive after reports of two affairs, one involving a suspected Chinese spy. CFO Colette Kress has been named interim CEO. Nvidia's shares fell over 4% after the news, reflecting market concerns.

    bbc.co.uk168 pointsDiscussion
  10. 10
    Coding agentsHacker News

    AgentRun open-source platform adds self‑improving, token‑efficient agents

    AgentRun is an open‑source system that adds a control plane for self‑improvement and durable execution to existing agent frameworks. It claims agents become smarter, more fault‑tolerant and use fewer tokens per run, with case studies showing cost reductions in code review and classification tasks.

    github.com90 pointsDiscussion
  11. 11
    Dev toolsSimon Willison

    AWS releases official emulator for local testing of its services

    AWS has open‑sourced an emulator written in Rust that lets developers run local copies of many AWS services for testing, avoiding the need for paid API keys. The emulator currently runs via Docker on macOS and Windows, simplifying integration into test suites.

    simonwillison.net
    AWSalternatives
  12. 12
    AIDevHunt launch

    Wiro AI offers unified API for 1,000+ generative models and agents

    Wiro AI provides a single API to access over a thousand image, video, audio, 3D, and language models, allowing developers to chain them into workflows and deploy AI agents. It supports async tasks via webhooks and WebSockets, includes an OpenAI‑compatible endpoint, SDKs, and pay‑as‑you‑go pricing.

    16 points
    Wiro AIalternatives
  13. 13
    Dev toolsDevHunt launch

    Review Router posts GitHub pull requests to designated Slack channels

    Review Router monitors GitHub pull requests and posts them to selected Slack channels, tagging appropriate reviewers. The Slack messages stay updated with new commits, comments, approvals, and merge status, helping teams coordinate reviews using existing tools and configurable rules.

    15 points
    Review Routeralternatives

Archive

22 more days

Built something developers should hear about? Launch it on DevHunt: the week’s top launches make the news here.