惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

N
News and Events Feed by Topic
Malwarebytes
Malwarebytes
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
Cybersecurity and Infrastructure Security Agency CISA
F
Future of Privacy Forum
C
Cisco Blogs
T
The Exploit Database - CXSecurity.com
A
Arctic Wolf
S
Securelist
K
Kaspersky official blog
S
Schneier on Security
T
ThreatConnect
T
Tenable Blog
Spread Privacy
Spread Privacy
T
True Tiger Recordings
AWS News Blog
AWS News Blog
F
Fox-IT International blog
量子位
T
Threatpost
V
Vulnerabilities – Threatpost
C
CERT Recently Published Vulnerability Notes
Cisco Talos Blog
Cisco Talos Blog
GbyAI
GbyAI
宝玉的分享
宝玉的分享
腾讯CDC
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
Cyberwarzone
Cyberwarzone
有赞技术团队
有赞技术团队
S
SegmentFault 最新的问题
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
Visual Studio Blog
U
Unit 42
雷峰网
雷峰网
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Simon Willison's Weblog
Simon Willison's Weblog
O
OpenAI News
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
The GitHub Blog
The GitHub Blog
The Register - Security
The Register - Security
MyScale Blog
MyScale Blog
小众软件
小众软件
A
About on SuperTechFans
Last Week in AI
Last Week in AI
Y
Y Combinator Blog
博客园 - 三生石上(FineUI控件)
美团技术团队
Google Online Security Blog
Google Online Security Blog
P
Proofpoint News Feed
MongoDB | Blog
MongoDB | Blog

Hacker News: Show HN

Show HN: I built a TikTok style video debate app Show HN: Simple Sprite Sheet Generation Show HN: Worldnotes – infinite notes in-browser canvas Show HN: Brew-browser – A native macOS GUI for Homebrew GitHub - aloth/cred-1: CRED-1: An Open Multi-Signal Domain Credibility Dataset (2,672 domains) Show HN: TalkTimer, a micro-SaaS run by an AI agent team Trickster's Table invest-like - AI value-investing: best-tier consensus beat S&P 500 by +72.7% GitHub - kimjune01/swebench-verified: Reproducible recon/craft/audit agent pipeline for SWE-bench Verified. Official-graded, codex-attested, GPL-3.0. Run it yourself. GitHub - mupt-ai/context-drop: cli tool to make sharing context between remote agents dead easy Multiple Real Desktops for Windows GitHub - lionello/han64: Handling Chinese text on the Commodore 64 Show HN: Strudel – Generate commit messages via Apple's on-device LLM Show HN: Audiomass – a free, open-source multitrack audio editor for the web move-reminder The Front Page HtmlUnit – Welcome to HtmlUnit GitHub - kouhxp/textsnap: Snap any image, screenshot, or webpage into plaintext. No GPU. No cloud. One command. Show HN: Pro Health Ledger – An open-source, net-neutral reputation system iPhone 版“Today” - App Store LLMRequirements.com — Hardware for Local LLMs Show HN: Hookwarden – npx tool to find and fix webhook HMAC bugs (JS/TS/Py/PHP) Frello — A small revolt against bloated software Career tools for data professionals | Datamata Studios Show HN: Kanban CLI (A local-first, agent-first task manager for the terminal) Show HN: Fleet – Python supervisor for running coding agents in parallel TravElly | A travel diary app for kids TapToyPia Show HN:An LED display app that lights up concerts, events, and fan moments Show HN: Logo Fonts Home | Qavvāli Wiki Show HN: Panorama – Review Code, Faster Show HN: Slow Code, a monthly meetup to practice coding by hand GitHub - abakh/nbsdgames: A package of 21 new, improved, text-based modern games. Some are entirely original ideas. Best and lightest! Let's Jam Show HN: CurRant->Screw Google scourge, help people notice what is worth a look Fruitsy Show HN: World Cup 2026 free family and friends prediction platform AgentLens — Know if your AI features are actually working Planet Maiko Specter — Use AI on your Ghost blog, locally Money Me - Personal Financial Management Smart Runner: Adaptive Running Plans for iPhone and Apple Watch Show HN: nsS3ui – A non sucking GUI for S3 Show HN: Vibe-coded Steam, but in the browser AI Model Idle · 인공지능 키우기 Show HN: Running BitNet b1.58 inside DRAM by breaking DDR4 timing rules GitHub - muhammadmuzzammil1998/pack-src: Recursively pack source code directories into clean ZIP archives — fast, smart, and ignore-aware. Streakout: Visualize Your Apple Health Workout Data Show HN: Memory for LLM apps that cuts input tokens up to 80% (avg 68%) AI Chess Coach — Know Why Every Move Matters Gemini Omni Flash Video Generator & Editor | Vivify Show HN: Invoker, an IDE for orchestrating massively parallel agents Show HN: I built a RAG and knowledge graph agent that runs locally Clankerfights Show HN: Fed.run – online collaborative Rust IDE and Markdown editor GitHub - EliotAndres/SimStream: SimStream is a library to stream iOS simulators from your Mac to your iPhone (or any web browser) Solana Index | Slot-Based Token Balance API GitHub - mainline-org/mainline: Git-native memory for coding agents. Repo memory before the diff. CostHawk - Track AI Adoption, Cost, and Rollout Across Your Team Show HN: Calculator Music – play songs with number keys in the browser Show HN: First MCP server for Guesty property mgmt – 43 tools, open source GitHub - stukenov/rav2d: AV2 video decoder in Rust — full port of dav2d C logic to memory-safe Rust. 47K lines, 786 tests. Assembly DSP stays via FFI. Show HN: I built a powerful RAG and knowledge graph agent that runs locally Show HN: Directionally bad – a newsletter about risks of AI centralization Welcome chord-commander GitHub - klimentij/klimkit: Agentic engineering across machines, under control. Congress Disclosure Watchlist Digest - TinyOps Studio GitHub - arthurzhu29/larksson Brev - Frictionless Notes - Apps on Google Play TruLayer — Evals, Closed Control Loop & Auto-Rollback for Production AI GitHub - pilatesjs/pilates: Headless flex layout engine for terminal UIs. NOW and CSCO Politician Trading Claims ThinkLLM — Think through your LLM choices Show HN: Waiting for AI Grand Prix racing SIM? Me too So I made one WAR.GOV/UFO Microfilm5 Show HN: Claude Code for Customer Support Show HN: Agentikus Purr - Apps on Google Play atom.plumocracy.com Show HN: BonzAI – self-sovereign, local LLM inference in the browser GitHub - T0nd3/logatory: Local-first log analysis with PII redaction, threat detection, anomaly detection and LLM insights — CLI, web dashboard and REST API GitHub - doshareme/synchole: P2P Data Sync Protocol GitHub - secluso/core: A privacy-preserving Raspberry Pi home security camera that uses advanced end-to-end encryption. Show HN: Microcodegen.py – PRD → FastAPI app, one file, no LLM calls iPhone 版“Today” - App Store ScrollLaunch — Launch Your Product. Get Seen Weekly. GitHub - ppserapiao/mneme: the open, user-sovereign memory layer for AI. local-first · client-side encrypted · open protocol. your memory. your keys. every model. Datapoint AI Home Codeep — Go Deep into Code OpenRig — Local control plane for multi-agent coding topologies GitHub - allenwu-blip/mcpaudit: Static pre-install security scanner for MCP (Model Context Protocol) servers — `npx mcpaudit <path>` flags command injection, credential/env exfiltration into LLM-visible output, over-broad filesystem/tool scope and dynamic eval before you wire a server into your agent. Show HN: Quit All, an iOS app with an SOS mode for cravings GitHub - dmichael-fastly/fastly-examples-live-betting-fanout: A working example of distributing live game scores and betting odds to millions of concurrent users without overwhelming origin — built on Fastly's edge stack. 404 Page Generator — Make your 404 page a needle-mover Show HN: Neuz, a self-hosted news dashboard curated by Claude Senior SWE interview prep — Semicolony GitHub - DefangLabs/pulumi-defang: Defang Pulumi providers - Take your app from Docker Compose to a secure and scalable cloud deployment with Pulumi.
Assemblr
adityahv · 2026-05-25 · via Hacker News: Show HN

forengineeringteams

We watch how your engineering team ships
and fix gaps in your process.

Assemblr reads every PR, commit, review, and message across GitHub, Slack, and Linear — and your actual codebase — names the routines your team keeps doing on autopilot, and turns each one into a ready-to-run agent with citations to the exact file and line.

Not a context brain. We don't hoard your data and re-sell search. We watch how your team works, ground every claim in the code, and ship the agents that close the loop.

Your team's pattern  ·  live12 patterns  ·  47 edges

pull_request.openedreview.requestedci.completedreview.completedpull_request.mergeddeploy.startedslack.messagelinear.transitionincident.createdpostmortem.scheduled

[14:32:07] vercel/turbo — a process step got skipped twice this week · 2 incidents · trace=a3f2

— Public Mirrors —

● TheAgents

Agents that fix the gaps the Mirror surfaces.

Never speculative. Every agent inherits the routine's tone, timing, and identity hints from the Mirror.

● ThePatterns

A vocabulary for what your team actually does.

A growing dictionary of patterns of work. Into your standups, your 1:1s, your board memos.

Pattern · Description · Frequency

  • Cold reviewPR opened and merged with reviewer = author or no approval

    ◆◆◆◇◇
  • Decay driftA routine that fired 80% of the time 30 days ago, now 40%

    ◆◆◆◆
  • Half-Friday shipDeploy after 3pm Friday with no rollback plan in PR

    ◆◆◇◇◇
  • Workflow gapCross-tool routine fires N-1 of N expected steps

    ◆◆◆◆◆
  • Load-bearing actorOne engineer holds 75%+ of a behavior class

    ◆◆◆◇◇
  • Orphan ticketLinear issue closed without a code merge in 7 days

    ◆◆◆◆
  • Phantom standupStandup pattern ran 4+ weeks then stopped 7+ days ago

    ◆◆◆◇◇
  • Postmortem skipIncident channel created, no postmortem in 7 days

    ◆◆◆◆
  • Routine fadingA team habit moved from thriving to dormant within 60 days

    ◆◆◆◆◆
  • Silent mergePR merged with no Slack or release-notes followup

    ◆◆◆◆◆
  • Solo handoffLoad-bearing actor performs 80% of a behavior class

    ◆◆◇◇◇
  • Stale-design codeCode shipped while design doc untouched 30+ days

    ◆◆◆◇◇

● How itworks

Mine. Name. Mirror. Activate.

  1. 01

    Mine

    Patterns mined from your team's actual activity. No labeling. No templates.

  2. 02

    Name

    Patterns get plain-English names — silent merges, workflow gaps, fading routines — so you can talk about them out loud.

  3. 03

    Mirror

    A weekly briefing in the language of investigative journalism. Specific events, specific dates, specific patterns.

  4. 04

    Activate

    Once a routine has fired consistently, you activate it as an agent. One click. Inherits tone, timing, identity.

● The engineeringtrio

GitHub, Slack, Linear. The data the Mirror sees.

Read-only by default. We never write to your sources unless an agent explicitly does so on your behalf.

Existing Notion, Google, and Asana connections continue to ingest. New connections to those toolkits are paused while we focus on the engineering trio.

● A newcategory

What teams actually do, not what they declared.

Process Mining showed us what enterprise software actually does. Behavioral intelligence shows us what teams actually do. Same instinct — observe what's real, not what's declared — applied to a new substrate: humans plus SaaS, not bots plus ERP.

forengineeringteams

Start your team's Mirror.