LinkWord
Home
Directory
Articles
AI models
Tools
Pixel Plaza
Settings
ContactRSSFriend linksSubmit site
Privacy Policy·Disclaimer
陕ICP备2025083618号-2

Hot channels

AI ToolsDeveloper ToolsProductivity ToolsEntertainment & MediaJobs & Careers

LinkWord · Find great sites and reads

LinkWord · AI Directory & Site Recommendations

Search when you know what you want—or scroll on: articles, tools, and picks are just below.

You don’t need the whole site at once. Start wherever feels natural.

Pick a category and engine, then search. In-site directory and AI directory are under Common; external sites open in a new tab unless configured otherwise.

Browse the directoryRead a storyTry a tool

LinkWord

What is LinkWord? AI directory & online tools

LinkWord (linkwordx.site) is an AI directory and navigation-style site: it combines an AI tools directory, website recommendations, tech news, curated articles, and a large set of small online utilities—so you can discover great bookmarks and jump to what you need with search.

Search the directory from the home page, browse categories, read the latest articles, or open the toolbox for privacy-friendly, in-browser helpers for links, text, and data—no install or login required.

Browse the AI & website directoryRead tech news & curated articlesOpen the online toolbox

LinkWord online toolbox

A few crowd favorites live here; the full toolbox has 50+ more, all running locally in your browser.

UTM link builder and parser

Add or inspect utm_source, utm_medium, utm_campaign, and more for campaign tracking.

QR code generator

Create QR codes locally: size and colors, PNG/SVG export, WiFi/vCard templates, optional center logo.

JSON / YAML tools

Format or minify JSON, or convert between JSON and YAML.

AI token calculator

OpenAI models via tiktoken; China models via common heuristics and cl100k/o200k proxies for rough cost and context planning.

Browse all tools

Directory, articles & tools — three ways to explore

Find sites, catch up with reads, or knock out a quick task in the browser. It all works best with the search box above.

Land on the right site

Filter with keywords—or let AI understand what you need—so you spend less time bouncing between tabs.

Reads that go a little deeper

Tech, AI, and product pieces for a commute scroll or a longer weekend read.

Little tools, no install

Links, text, data, color helpers, and more—open, use, close. No account required.

Where to next?

If you already know what you need, head to directory search. If you’d rather read or play with a tool, the doors below are open.

Search the directoryBrowse articlesOpen the toolbox
Suggest a site / say hiSubscribe via RSS

Follow on WeChat

WeChat account QR code

Editor's picks & trending AI sites

Not sure what to search yet? Start with what we're featuring, then peek at what others have been opening lately—you might find your next favorite bookmark.

Open link

Top clicked AI sites

Sorted by clicks

1Site icon for “GitHub”GitHub5 clicks2Site icon for “Alibaba Careers”Alibaba Careers5 clicks3Site icon for “Loot Drop - Database of Startup Failures”Loot Drop - Database of Startup Failures5 clicks4Site icon for “dverso Laundry — Background Removal”dverso Laundry — Background Removal4 clicks5Site icon for “CodePen”CodePen3 clicks6Site icon for “AcFun”AcFun3 clicks7CChuangge Toolbox — A collection of free small tools, ready to use by simply opening the webpage, with files processed as much as3 clicks8Site icon for “Railway”Railway2 clicks9Site icon for “Gamma — AI Presentations & Website Builder”Gamma — AI Presentations & Website Builder2 clicks10Site icon for “Conch AI Video Generator”Conch AI Video Generator2 clicks
Browse directory

Tech articles worth reading

Cover image for “Codemod Grep, So Very Bright, writing-eval — Three Tools Worth Trying | 2026-08-24”

Codemod Grep, So Very Bright, writing-eval — Three Tools Worth Trying | 2026-08-24

Three tools worth trying this week: Codemod Grep (AST structural code search), So Very Bright (free HDR logo maker), and writing-eval (deterministic AI writing style checker).

Cover image for “Omarchy, OpenLogi, Histiq — Three Tools Worth Checking Out | 2026-08-23”

Omarchy, OpenLogi, Histiq — Three Tools Worth Checking Out | 2026-08-23

Three tools worth checking out: Omarchy (a polished Linux desktop by Basecamp), OpenLogi (a Rust-native Logitech mouse manager), and Histiq (local semantic search for browser history and PDFs).

Cover image for “2026-08-22 Picks: OzBrain, Rust Glancer, Groovebox”

2026-08-22 Picks: OzBrain, Rust Glancer, Groovebox

2026-08-22 picks: OzBrain (shared brain for AI agents), Rust Glancer (100x less RAM Rust LSP), Groovebox (self-hosted music archival engine).

AI model leaderboard

Top 5 preview per category—chat, image, and video.

RankModelProvider
ScoreEditorial composite score; higher ranks higher
Context (K)Context window size (thousand tokens)
Input $Input token price (USD per 1M tokens)
Output $Output token price (USD per 1M tokens)
MMLUMassive Multitask Language Understanding accuracy (%)
HumanEvalCode generation benchmark pass rate (%)
EloArena Elo from human preference battles; higher is stronger
1
G
GPT-5.5
OpenAI's latest flagship model with 1050K context, leading AI reasoning and coding capabilities
OpenAI98.0105053091.5091.401420
2
C
Claude Fable 5
Anthropic's most capable model, positioned above Opus tier. Public Mythos-class model with 1M context, scoring >10% higher than Claude Opus 4.8 on key benchmarks. Adaptive thinking only.
Anthropic97.010001050———
3
G
Gemini 3.5 Pro
Google DeepMind's flagship model with 1000K context window, comprehensive capabilities
Google DeepMind96.010001.5099189.501400
4
G
GPT-5.6 Sol
OpenAI's flagship GPT-5.6 model. HealthBench Professional 60.5%, High on cybersecurity and biosecurity evals. New API Fast mode: 2.5x faster than Standard at 2x price, no change in intelligence (2026-07-30).
OpenAI96.010504240—0
5
G
Grok 4.6
xAI's flagship model released Aug 12, 2026 (now operating as SpaceXAI). Scores 61 on the AA Intelligence Index, level with GPT-5.6 Sol. Strong in agentic work: GDPval-AA v2 Elo 1753, Terminal-Bench v2.1 88.4%, τ³-Banking 50.7%. Priced at $2/$6 per 1M tokens with 500K context; ~$0.84 per task, on par with Kimi K3.
xAI95.0500260—1753
View full leaderboard

Tech news & curated articles

Fresh articles and takes—subscribe with RSS if you want updates in your reader.

View all →
Cover image for “Codemod Grep, So Very Bright, writing-eval — Three Tools Worth Trying | 2026-08-24”New

Codemod Grep, So Very Bright, writing-eval — Three Tools Worth Trying | 2026-08-24

Three tools worth trying this week: Codemod Grep (AST structural code search), So Very Bright (free HDR logo maker), and writing-eval (deterministic AI writing style checker).

8/24/2026

Cover image for “Omarchy, OpenLogi, Histiq — Three Tools Worth Checking Out | 2026-08-23”New

Omarchy, OpenLogi, Histiq — Three Tools Worth Checking Out | 2026-08-23

Three tools worth checking out: Omarchy (a polished Linux desktop by Basecamp), OpenLogi (a Rust-native Logitech mouse manager), and Histiq (local semantic search for browser history and PDFs).

8/23/2026

Cover image for “2026-08-22 Picks: OzBrain, Rust Glancer, Groovebox”New

2026-08-22 Picks: OzBrain, Rust Glancer, Groovebox

2026-08-22 picks: OzBrain (shared brain for AI agents), Rust Glancer (100x less RAM Rust LSP), Groovebox (self-hosted music archival engine).

8/22/2026

Cover image for “Vomit, ParqDB, DumpSort: Three Useful Tools to Try | 2026-08-21”

Vomit, ParqDB, DumpSort: Three Useful Tools to Try | 2026-08-21

Three hot tools worth trying: Vomit cleans up Claude 5 verbose output, ParqDB runs vector search in the browser, and DumpSort auto-renames your screenshots into a zip.

8/21/2026

Cover image for “GLM-5.3: Zhipu AI's Coding Model Leaps Forward with Unexpected Cyber Capabilities | 2026-08-20”

GLM-5.3: Zhipu AI's Coding Model Leaps Forward with Unexpected Cyber Capabilities | 2026-08-20

Zhipu AI released GLM-5.3, achieving a 50% coding improvement and open-source SOTA on cyber vulnerability discovery through post-training RL scaling alone.

8/20/2026

Cover image for “fx, MoneyPrinterTurbo, OpenViking: Three Developer Tools Worth Trying | 2026-08-20”

fx, MoneyPrinterTurbo, OpenViking: Three Developer Tools Worth Trying | 2026-08-20

Three hot developer tools this week: Vercel's minimalist coding agent fx (6MB, written in Zig), the 110K-star AI short video generator MoneyPrinterTurbo, and ByteDance's self-evolving context database for AI agents OpenViking.

8/20/2026

Cover image for “Daily Picks: MathCode, Wild Static, GitFC | 2026-08-17”

Daily Picks: MathCode, Wild Static, GitFC | 2026-08-17

Three picks today: MathCode turns plain-language math problems into Lean 4 formal proofs (626 stars on GitHub); Wild Static is a public AI experiment with a single shared memory that never resets; GitFC maps your GitHub activity into an EA FC-style player card, fully client-side. All three are worth a look today.

8/17/2026

Cover image for “2026-08-16 Picks: Printytron, Waku, SugarTrack”

2026-08-16 Picks: Printytron, Waku, SugarTrack

Three picks today: Printytron turns plain English into printable STL files, Waku unifies your local coding agents in a native Rust app, and SugarTrack is a fully offline blood sugar logbook.

8/16/2026

Cover image for “Qwen3.8-27B Open Weights Released: 27B Model Beats Claude Opus 4.6 Max on Key Coding Benchmarks | 2026-08-15”

Qwen3.8-27B Open Weights Released: 27B Model Beats Claude Opus 4.6 Max on Key Coding Benchmarks | 2026-08-15

Alibaba open-sourced Qwen3.8-27B on Aug 14: a 27B dense multimodal model with native image/video understanding and 262K context (up to 1M). It beats Claude Opus 4.6 Max on several coding benchmarks (SWE-bench Pro 61.7, DeepSWE 42.2) and runs on consumer hardware. DeepSeek also shipped V4-Pro GA plus peak/off-peak pricing.

8/15/2026

Cover image for “Gemini 3.7 Flash, DeepSeek Harness, GPT-5.6 Sol Ultrafast, Mistral OCR 4.1: AI Roundup | 2026-08-14”

Gemini 3.7 Flash, DeepSeek Harness, GPT-5.6 Sol Ultrafast, Mistral OCR 4.1: AI Roundup | 2026-08-14

Four AI releases landed on August 13: Google's Gemini 3.7 Flash at half the price, DeepSeek's open-source Harness agent framework (MIT, everything is a plugin), OpenAI and Cerebras' GPT-5.6 Sol Ultrafast tier (up to 750 tokens/s), and Mistral OCR 4.1.

8/14/2026

Cover image for “Bullet, MCP-stama, Snippety: Three Dev & Productivity Tools | 2026-08-14”

Bullet, MCP-stama, Snippety: Three Dev & Productivity Tools | 2026-08-14

Three picks from HN today: Bullet, the fast YC S26 coding agent; mcp-stama, a Rust MCP server under 10MB; and Snippety, a template-engine text expander for macOS and iOS.

8/14/2026

Cover image for “Ballet, Decant, GreenTree: Three Developer Tools to Try | 2026-08-13”

Ballet, Decant, GreenTree: Three Developer Tools to Try | 2026-08-13

Today's picks: Ballet workflow automation that writes API integrations from a description, Decant local-first CLI for analyzing coding agent token spend, and GreenTree, a Rust tool that caches test results by Git tree. With real HN community feedback and use-case notes.

8/13/2026

Cover image for “Grok 4.6, DeepSeek V4 Pro 0813, and Open-Weight Qwen3.8-2.4T: Three Major AI Releases | 2026-08-13”

Grok 4.6, DeepSeek V4 Pro 0813, and Open-Weight Qwen3.8-2.4T: Three Major AI Releases | 2026-08-13

Three major releases in 24 hours: xAI's Grok 4.6 matches GPT-5.6 Sol on the AA Intelligence Index (61), DeepSeek ships the official V4 Pro 0813 with much stronger agent capabilities, and Alibaba Qwen open-sources the 2.4T-parameter Qwen3.8-2.4T-A95B — the largest open-weight model ever.

8/13/2026

Cover image for “Three developer tools: Git-knife, Line9, p0rt | 2026-08-12”

Three developer tools: Git-knife, Line9, p0rt | 2026-08-12

Three fresh developer tools from Hacker News: Git-knife, a desktop app that edits git commit metadata like a spreadsheet; Line9, a Mermaid rendering engine with its own layout; p0rt, a macOS menu bar manager for dev servers and Docker containers.

8/12/2026

Cover image for “NVIDIA Launches Nemotron 3.5 Lightning: Open 30B Agentic Model with 4x Faster Output | 2026-08-12”

NVIDIA Launches Nemotron 3.5 Lightning: Open 30B Agentic Model with 4x Faster Output | 2026-08-12

On August 11, NVIDIA released Nemotron 3.5 Lightning, an open 30B (3B active) MoE agentic model with a Mamba-2 + MoE + Attention hybrid architecture and up to 1M token context, plus the open-source NeMo Switchyard routing library. NVIDIA claims up to 4x faster output and ~30% faster agentic task completion. Available on Hugging Face, ModelScope, OpenRouter, and as a NIM microservice; runs locally on RTX PCs and DGX Spark under the commercial-friendly OpenMDW-1.1 license.

8/12/2026

Cover image for “2026-08-11 Picks: GPUHour, SendPage, Insidedb”

2026-08-11 Picks: GPUHour, SendPage, Insidedb

Three useful tools today: GPUHour compares live cloud GPU rental prices, SendPage turns AI-generated HTML into shareable links, and Insidedb explains database internals with interactive animations.

8/11/2026

Cover image for “Meta Muse Glimmer: 30B Open-Weight Local Agent Model, Under 20GB Quantized | 2026-08-11”

Meta Muse Glimmer: 30B Open-Weight Local Agent Model, Under 20GB Quantized | 2026-08-11

Meta Superintelligence Labs open-sources Muse Glimmer, a 30B Apache 2.0 agentic model for on-device use. Distilled from the flagship Muse Spark and quantized to under 20GB, it runs on a single consumer GPU. Meta claims it beats Gemma4-31B and Qwen3.6-27B on agentic benchmarks, with DFlash speculative decoding delivering 3.1x faster generation on RTX 5090.

8/11/2026

Cover image for “witr, T3 Code, Agent Skills: Open-Source Dev Tools Picks | 2026-08-10”

witr, T3 Code, Agent Skills: Open-Source Dev Tools Picks | 2026-08-10

2026-08-10 picks: witr (process tracing CLI, 21k stars), T3 Code (open-source control plane for coding agents), and Agent Skills (Addy Osmani's production-grade engineering skill packs, 85k stars) - three trending open-source dev tools.

8/10/2026

Cover image for “Tura, OutageDeck, tweet.download: Three Tools Worth Trying | 2026-08-09”

Tura, OutageDeck, tweet.download: Three Tools Worth Trying | 2026-08-09

Three picks from today's HN: Tura, an open-source agent runtime with an 80% DeepSWE pass rate and 77.5% fewer tokens; OutageDeck, outage alerts covering 172 vendors' status feeds; and tweet.download, which turns tweets into HD images or videos. All three are now in the nav directory.

8/9/2026

Cover image for “DeepSeek V4 Flash 0731 ARC-AGI Results: 89% on ARC-AGI-1, 61.4% on ARC-AGI-2 | 2026-08-09”

DeepSeek V4 Flash 0731 ARC-AGI Results: 89% on ARC-AGI-1, 61.4% on ARC-AGI-2 | 2026-08-09

ARC Prize published verified ARC-AGI results for DeepSeek V4 Flash 0731: 89.0% on ARC-AGI-1 and 61.4% on ARC-AGI-2 at max effort, costing $0.02-$0.04 per task — comparable to GPT-5.6 Luna at roughly 2x lower cost. Official agent benchmarks far exceed V4-Pro-Preview; open weights run on a single MI300X. DeepSeek also announced a significant API price increase is coming.

8/9/2026

Cover image for “2026-08-08 Picks: textlog, Agent Tunnels, Jobman”

2026-08-08 Picks: textlog, Agent Tunnels, Jobman

Daily picks: textlog, an open-source text-only microblog; Agent Tunnels, secure collaboration between coding agents across companies; and Jobman, a daemon-less CLI job manager. All three trended on Hacker News this week.

8/8/2026

Cover image for “US DOE Launches Genesis Open Models Initiative with Trillion-Parameter Genesis-Science-1 | 2026-08-08”

US DOE Launches Genesis Open Models Initiative with Trillion-Parameter Genesis-Science-1 | 2026-08-08

The U.S. Department of Energy launched the Genesis Open Models Initiative with Arcee AI, unveiling Genesis-Science-1, a trillion-parameter-class open-weight model for scientific research across materials, energy, fusion and biology. Weights and a technical report are slated for release later this year.

8/8/2026

Cover image for “2026-08-07 Picks: Channels SDK, Silo, Gitdebt”

2026-08-07 Picks: Channels SDK, Silo, Gitdebt

Today's picks: Channels SDK brings AI agents natively into Slack/Teams/Discord/Telegram; Silo is a Pigsty-maintained MinIO fork for S3-compatible storage; Gitdebt generates live GitHub repo health reports.

8/7/2026

Cover image for “Qwen3.8 Max Tops Agentic Index, GPT-5.6 Luna Goes Free: AI News Roundup for August 6 | 2026-08-07”

Qwen3.8 Max Tops Agentic Index, GPT-5.6 Luna Goes Free: AI News Roundup for August 6 | 2026-08-07

On August 6, Alibaba's Qwen3.8 Max was ranked first overall on Artificial Analysis' Agentic Index, with 2.4T parameters and open weights coming for the first time at Max scale. The same day, OpenAI updated GPT-5.6 Sol and made Luna the default model for free users with unlimited text chats.

8/7/2026

Load more