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

Vercel News
Vercel News
Recorded Future
Recorded Future
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
The GitHub Blog
The GitHub Blog
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Google DeepMind News
Google DeepMind News
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Microsoft Azure Blog
Microsoft Azure Blog
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
M
MIT News - Artificial intelligence
云风的 BLOG
云风的 BLOG
Y
Y Combinator Blog
N
News | PayPal Newsroom
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Help Net Security
Help Net Security
博客园 - Franky
SecWiki News
SecWiki News
Recent Announcements
Recent Announcements
T
Troy Hunt's Blog
The Register - Security
The Register - Security
The Last Watchdog
The Last Watchdog
Webroot Blog
Webroot Blog
S
Security Affairs
博客园 - 司徒正美
S
Schneier on Security
I
InfoQ
博客园_首页
www.infosecurity-magazine.com
www.infosecurity-magazine.com
T
Threat Research - Cisco Blogs
Forbes - Security
Forbes - Security
腾讯CDC
N
Netflix TechBlog - Medium
N
News and Events Feed by Topic
Cloudbric
Cloudbric
T
The Exploit Database - CXSecurity.com
P
Proofpoint News Feed
A
About on SuperTechFans
Engineering at Meta
Engineering at Meta
Recent Commits to openclaw:main
Recent Commits to openclaw:main
B
Blog
V
Vulnerabilities – Threatpost
C
Check Point Blog
Google DeepMind News
Google DeepMind News
Google Online Security Blog
Google Online Security Blog
C
Cyber Attacks, Cyber Crime and Cyber Security
Hacker News - Newest:
Hacker News - Newest: "LLM"
C
Cisco Blogs
Schneier on Security
Schneier on Security
O
OpenAI News
K
Kaspersky official blog

Show HN

GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - 0gsd/enough: a personal language system for planning, writing, and translation. GitHub - Kaelio/ktx: ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
Dodger | The intelligence layer for product
Dodger AI, Inc. · 2026-06-25 · via Show HN

New · Linear, Slack & MCP integrations

The product development engine, end to end.

Dodger runs every stage of product development — from research and user stories to design and testing — grounded in your real product data.

Most teams still decide what to build like it’s 2015.

Weekly roadmap sync 11:00

The meeting where the loudest voice wins.

product

Users are asking for this 🙏

— it was one user.

roadmap.csv Confidence

A roadmap nobody in the room fully believes.
“strategy”
A gut call wearing a strategy costume.

Then you spend three weeks of suddenly-cheap engineering building it — and it lands with a thud.

You didn’t get faster. You got faster at being wrong.

Everything you have, into one clear plan.

Point Dodger at what you already have: your docs, your roadmap, your designs, your data. It reads all of it and hands back specific, ranked direction: what to build, what to skip, and why.

Support tickets PRD & docs Linear issues Figma frames PostHog

What to build first Build-ready spec What to skip Risks to watch

Your synthetic users test it. Before and after it ships.

Dodger puts synthetic users on your actual screens and watches how they react — catching friction before you ship, and the reasons people leave after.

Talk to your users.
Anytime.

Interview synthetic users grounded in your real data. They tell you what to build before you ship, and what's broken after.

  • Grounded in your research, not generic personas
  • Pulls live context from PostHog, Granola, Figma & more
  • Pushes back on your assumptions in real time

M Maya Torres Working parent · 34 · Decision fatigue Available now

What's the first thing you'd want when you open the app?

Honestly? Just tell me what to cook tonight with what I already have. By 5pm I've made 200 decisions and I want one made for me.

Ask Maya anything…

Built to live where decisions actually get made.

M Maya TorresWorking parent · 34 Live · 02:14

“Just tell me what to cook tonight with what I already have.”

Hold to talk Interrupt

Voice interviews

Don’t type — talk. Run a discovery session out loud with any synthetic user, the way you would a real one, and let them interrupt and push back in real time.

It doesn’t ask you to trust it. It shows its work.

Anyone can generate a confident answer. Dodger gives you a decision you can audit — pull any recommendation and walk it all the way back to the source it came from.

It works where you do.

No new dashboard to check. Dodger plugs into the tools your team already uses every day.

Cycle 24Reprioritized

Ten-second mobile loggingHigh impact

Offline capture & syncBuild

Full dashboard rebuildNo signal

+

Keep the roadmap honest.

Every cycle, Dodger weighs what's queued in Linear against real user signal, promoting the work that moves the needle and flagging the tickets nobody actually asked for.

+

Test designs before you build them.

Wireframes land in Figma, synthetic users run the real flows, and the friction points come back as comments, so you fix them before a single component ships.

+ +

Ship straight from spec to code.

Hand the validated spec to your editor of choice: user stories, acceptance criteria, and the research behind every decision, ready to build the moment you are.

dodger.mdValidated

User story

As a field rep, I can log a call in under 10 seconds, one-handed.

Capture works offline and syncs later

Primary action reachable with one thumb

Ready for CursorClaude CodeCodex

Simple, predictable pricing.

Every plan runs the full pipeline — research, definition, and validation. Pick the one that fits how much you ship.

Free Try the full pipeline once, free.

$0/ month

No credit card required. Sign up

What's included 1 run / month 1 project, up to 3 personas 250 credits / month Personas, interviews & ranked insights Recommendations & a wireframe starting point

Starter For solo builders shipping their first product.

$99/ month

Billed monthly. Cancel anytime. Sign up

What's included 10 runs / month 10 projects, up to 6 personas each Personas, interviews & ranked insights Wireframes & design research Chat refinement & iterations Shareable links & Markdown export

Most popular Pro For teams shipping every week.

$249/ month

Per workspace. Unlimited seats. Sign up

Everything in Starter, plus 30 runs / month 30 projects, up to 12 personas each Usability simulation & scoring PDF, MCP & clipboard export Slack, Linear & PostHog integrations Priority processing, faster runs

Pro+ For heavy use, with no limits.

$499/ month

Per workspace. Unlimited seats. Sign up

Everything in Pro, plus Unlimited runs / month 20,000 credits / month Unlimited wireframe iterations Highest-priority processing

Team Seats, roles, and pooled credits for your whole team — one shared workspace, one invoice. From 3 seats.

Book a demo

Enterprise SSO / SAML, audit logs, DPA, custom volume, and dedicated support with SLAs.

Book a demo

Frequently asked questions

The questions teams actually ask before switching to Dodger. Can’t find yours? Get in touch or book a demo.

How is Dodger different from tools like Dovetail, Productboard, or Pendo?

Those tools organize inputs — Dovetail organizes research, Productboard organizes roadmaps. Dodger answers the question they leave open: what to build next. It reads from your research, analytics, and roadmap tools as inputs, then produces the decision itself — backed by evidence, with a spec, a design starting point, and an engineering breakdown.

How accurate are Dodger’s recommendations?

Every recommendation traces back to its sources — the interview quotes, analytics, tickets, and calls behind it — and carries an honest confidence label: strong signal, worth testing, or early hypothesis. You’re never asked to trust a black box; you see the evidence and decide for yourself. If one’s off, you stay in control: dig into the sources, adjust the scope, or re-run a stage.

Does Dodger replace my PM team?

No — it removes the synthesis grind PMs dread: reading dashboards, tagging interview clips, rewriting the same status doc every week. That frees them for the work that actually moves the product — customer relationships, judgment calls, and cross-functional alignment. Teams adopt Dodger to ship faster with the headcount they already have.

What tools does Dodger integrate with?

Granola (meeting notes), Linear (two-way issue sync), Slack (insights & digests), and PostHog (persona calibration) are live today. Rolling out next: Pylon (support tickets), Jira, Notion, GitHub, and webhooks. Dodger is also a remote MCP server, so coding agents like Claude Code, Cursor, and Codex can pull your stories, personas, and wireframes directly. See the full list on the integrations page.

Does Dodger use my data to train models?

No. Your data is never used to train Dodger’s models or any third-party model. It’s processed only to produce output for your own workspace — stored in the US on AWS via Supabase, scoped to your workspace and never shared across customers — and our AI provider handles it under a no-training agreement.

Is there a free trial?

There’s no separate time-boxed trial — the Free plan is the trial. It runs the full pipeline end-to-end, no credit card required, so you can see real output before you ever pay. Upgrade to Starter, Pro, or Pro+ whenever you’re ready.