Lazer — Music that feels like yours
Lazer is a quiet, refined open-source cross-platform music player for Windows and Android.
2
DEV TRENDS / DAILY DISCOVERIES
Sep 10, 2026 · What developers are building
Daily discoveries from developer communities, independent makers, and open source.
VibeToken
VibeToken is a unified API platform for devs and AI teams to access Chinese LLMs via official channels. It offers domestic direct connection, pay-as-you-go, centralized model selection, API key/usage management, chat/image/video generation
—
Flash Mask
Drag in an image, circle one or more regions needing edits, add notes, and copy JSON with image path, size and region coordinates for your AI agent—or export an equal-size black/white mask. Supports PNG/JPEG/WebP;
—
Tipsy Compass Beta
Recommends cocktails based on taste, currently available primarily as a WeChat Mini Program.
—
Cover Maker — Create a Great Cover for Your Content
A cover-making tool that creates consistently styled covers for video and social media apps.
—
Kiri: Screenshots, Recording, OCR, and Local Media Library
Kiri is an open-source macOS and Windows desktop tool for screenshots, annotation, local OCR, region recording, and a local media library. It supports search, tags, favorites, MP4/GIF, system audio, click highlights.
331
mimi: Real-time translated subtitles for playing videos
mimi: open-source real-time subtitle tool. Captures system audio, shows translated subtitles via provider APIs (Chinese, English, Japanese). Has immersive mode & movable click-through overlay. Mac (macOS 13+) & Windows preview. BYO API key.
215
MERVYX: Marketplace for AI Agents, APIs and Automation Services
MERVYX is a marketplace for verifiable outcomes from AI agents, APIs and automation services. Providers list services with pricing and acceptance criteria; buyers post tasks with budgets for quotes. Currently 0% commission.
—
ai-job-search-cn: One-Command Job Search Workflow for Chinese Job Platforms
One-command job hunt for China: aggregates Liepin, BOSS Zhipin, Zhaopin and 51job listings, filters hard requirements, scores matches, drafts greetings and Typst resume PDFs, tracks applications locally; you apply manually.
8
llm-web-grounding-proxy: OpenAI-Compatible Proxy for Real-Time Web Search and Citations
OpenAI-compatible reverse proxy that gives any LLM real-time web search with source citations. Residential proxy routing plus TLS fingerprint spoofing bypass Cloudflare/WAF blocks; FastAPI async, pip and Docker install.
—
Awesome-AI-Pedia: Daily-Updated DeepSeek Harness Plugins, AI Knowledge Base and Skills
A daily-updated open-source collection covering DeepSeek harness plugins, an AI knowledge base and a comprehensive skills catalog, maintained in the Awesome-AI-Pedia repository.
360
AntiBrow: Kernel-Level Anti-Detection Browser Driven by the Playwright API
Kernel-level anti-detection browser that alters fingerprints in C++ instead of injecting scripts. Exposes a standard Playwright BrowserContext over CDP, so existing Playwright scripts run unchanged. Free tier: unlimited local profiles.
334
Image to Image: AI Image Generation and Editing
AI image generation and editing service: upload an image and describe the changes to get new visuals that keep key elements like people, product details and composition.
—
AIradar: Compare AI Subscription Offers by Delivery Method, Term and Currency
AIradar compares public AI subscription quotes (ChatGPT, Claude) by product, delivery method, term and currency, with sources and timestamps, App Store regional price references, saved watches and calendar reminders.
19
HuiQuotation (慧报价): AI Quotation Tool for Foreign Trade with Free FOB/CIF Calculator
AI-driven foreign trade quotation tool: build a product library once, then auto-price selected items across EXW/FOB/CFR/CIF/DDP and generate bilingual CN-EN quotations in 30 seconds, exported as PDF or a read-only online link.
—
Toneferry: Stream Windows System Audio to Your Phone over LAN
Toneferry captures Windows system audio via WASAPI loopback and streams it over Node.js WebSocket to a phone browser on the same WiFi. No mobile app or virtual sound card needed; listen through the phone speaker or Bluetooth headphones.
5
330+ Open-Source Free Online Calculators and Unit Converters (MIT)
A comprehensive open-source collection of 330+ free online calculators and unit converters built with Next.js 14, covering finance, health, home and DIY, unit conversion, and productivity tools. MIT licensed.
0
ReadCLI: Terminal Novel Reader for macOS, Windows, and Linux
ReadCLI is a terminal novel reader supporting TXT and EPUB, with a local bookshelf, reading progress saving, bookmarks, search, customizable features, and several IDE-style interfaces.
30
ENZO — self-hosted BYOK AI workspace with agent builder
Project URL Category JS Project Title Selfhosted BYOK AI workspace: multiprovider chat, plainEnglish agent builder, scheduled runs Project A selfhosted AI workspace that runs on your own provider API keys (Groq, OpenRouter, NVI…
20
Agentic Deep Researcher: Open-Source Autonomous Multi-Hop AI Deep Research Engine
Open-source autonomous multi-hop AI research engine that decomposes questions into recursive sub-topics, scrapes 50–200 sources with proxy rotation and browser fingerprint spoofing, then synthesizes cited 5,000+ word reports.
—
ayghri / i-have-adhd
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
38.3K
bilawalsidhu / gods-eye-view
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.
24.2K
obra / superpowers
An agentic skills framework & software development methodology that works.
284.7K
alsk1992 / CloddsBot
Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains. Scans for edge, executes instantly, manages risk while you sleep.
1.6K
Tencent / teamai-cli
Make Every Team AI Native
3.8K
AlexsJones / llmfit
Hundreds of models & providers. One command to find what runs on your hardware.
35.7K
liquidslr / system-design-notes
Notes of the book System Desgin Interview - An Insider's Guide
18.8K
cathrynlavery / diagram-design
38 editorial diagram types for Claude Code, Codex, and Pi. Self-contained HTML + SVG. No shadows. No Mermaid slop.
37.7K
freestylefly / awesome-gpt-image-2
A prompt and case library for GPT Image 2 / 2.5 with 530+ examples, 20+ industrial-grade templates, reusable Skills, and a new same-prompt comparison section, each with full prompts and generation records.
30.8K
armory3d / armorpaint
Graphics Creation Tools
4.4K
diegosouzapw / OmniRoute
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot.
64.2K
JustVugg / colibri
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
27.5K
THU-MAIC / OpenMAIC
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
35.3K
nashsu / llm_wiki
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically.
18.1K
vercel-labs / skills
The open agent skills tool - npx skills
31.1K
hugo2046 / QuantsPlaybook
QuantsPlaybook replicates brokerage quantitative finance research reports for quantitative research and analysis.
6.1K
jaywcjlove / reference
A collection of developer cheat sheets covering common technologies, tools, and development workflows for quick reference and faster lookup.
15.2K
AstrBotDevs / AstrBot
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
40.3K
d2l-ai / d2l-zh
Dive into Deep Learning is a runnable, discussion-friendly deep learning textbook for Chinese readers; its Chinese and English editions are used for teaching at over 500 universities in 70+ countries.
80.5K
jeecgboot / JeecgBoot
JeecgBoot is an enterprise AI low-code platform that generates full-stack code and whole systems from prompts. AI Skills create workflows, forms, reports, and dashboards; built-in AI offers chat, knowledge base, orchestration, MCP plugins.
47.7K
higress-group / higress
🤖 AI Gateway | AI Native API Gateway
9.3K
itwanger / toBeBetterJavaer
An accessible, humorous Java learning guide covering Java fundamentals, concurrency, the JVM, enterprise development, and interview preparation, aimed at self-taught learners and job seekers.
17.6K
521xueweihan / HelloGitHub
Curates interesting, beginner-friendly open source projects on GitHub to help developers discover and learn from quality projects.
175.9K
xifangczy / cat-catch
Cat-catch is a browser extension for sniffing resources on web pages, helping users detect and capture media and other downloadable resources.
21.8K
iDvel / rime-ice
Rime input method configuration providing the Wusong Pinyin scheme and a long-term maintained Simplified Chinese dictionary.
19.3K
ScottSloan / Bili23-Downloader
Cross-platform open-source Bilibili video downloader with multithreaded acceleration, separate audio/video streams, danmaku and metadata retrieval, plus custom naming and categorization.
7.3K
langbot-app / LangBot
Production-grade platform for building agentic IM bots on Discord, Slack, Telegram, WeChat, Feishu, DingTalk, QQ, and Matrix, with agent/knowledge-base orchestration, plugins, and LLM integrations like ChatGPT, DeepSeek, Claude, Ollama.
17.7K
YSGStudyHards / DotNetGuide
A C#/.NET/.NET Core learning, work and interview guide collecting fundamentals, learning paths, hands-on development, coding tips, books/articles/videos, frameworks, tools, weekly news, interview questions, resume templates and jobs.
10.9K
notionnext-org / NotionNext
Turn your Notion workspace into a fast, customizable website. Built with Next.js + Notion API, with multi-platform deployment and no self-hosted server required.
11.8K
PlexPt / awesome-chatgpt-prompts-zh
A Chinese-language guide to ChatGPT prompts, collecting prompts for a variety of use scenarios and teaching users how to instruct the model effectively.
62.2K
iPhone Duo
Introducing iPhone Duo, the first foldable iPhone. When open, it’s the thinnest iPhone with the largest display ever — 50 percent larger than iPhone 18 Pro Max.
228
Suno v6
Suno v6 is a new generation of music models in three flavors: flagship v6, exploratory v6-wild, and free v6-mini. Edit one section or lyric without remaking the track, mash up your own songs, and start from text, audio, images, or video.
153
Gojo
Gojo puts local dictation, clipboard history, window controls, a file shelf, and media controls in your MacBook notch. Download a speech model, then dictate into the field you're using. Recognition runs on your Mac in local mode.
65
hob
Run complex agent work while staying in control. hob brings multiple models and independent workflows into one professional workspace. Agents can shape the workspace around each task, coordinate through it, and guide you inside it.
83
Drive
I spent a few years as a design lead on autonomous driving for Android Auto, then spent my weekends in a 27-year-old car doing the exact opposite. Drive came out of that gap.
74
Live Captions by Subanana
You speak once. Your audience scans a QR code, picks a language, and follows you live on their own phone — reading it, or hearing it. Put two languages on the big screen, or send a clean feed into OBS and vMix.
142
Desert Ant Labs
Desert Ant Labs builds small AI models that run on your phone or browser, no internet, no per-use cost. Instead of one big model doing everything, they make small ones, each nailing one task, across speech, text, and vision.
129
Thousand
Git-backed docs with real access control, in one markdown with folder-level access where teammates, outsiders and AI agents each see exactly their folders.
98
Modeinspect
Most software is designed twice: a picture first, then again in code. Intent drifts in between. Modeinspect is the AI design canvas for working on the real thing.
116
FreeScan.app
Audit any public URL for free, no signup. FreeScan uncovers problems and missed opportunities across SEO, AEO, GEO, security, accessibility, and design. Every finding includes evidence, why it matters, and how to fix it.
127
AI Observability by OpenObserve
Your agent cost $40 and took 34 seconds. But why? OpenObserve traces every agent session across models, tools, services, datastores, and user sessions so you can see exactly where time, money, and quality went.
269
Typewise Nova
Nova is the AI Operator that builds and improves your AI customer experience team, no developer required. Describe in plain language how customers should be handled and connect your tools.
279
Speechmark
Speechmark is a private macOS meeting-notes app. It records, transcribes, and summarizes meetings entirely on your Mac — decisions, action items, speaker-attributed transcripts. No bot joins the call, no account, one-time price.
92
Whip
Whip is a feed for the interactive expeirences. Discover and play games, 3D worlds, interactive stories, generative art, data visualizations, music toys, and more directly in your browser.
92
No matching projects
Try another keyword or category.
DEV TRENDS / COMMUNITY
Discuss this edition
Sign in with GitHub to share a thought, question, or useful follow-up.