The strongest technology signals from the past 30 days. One ranked view across AI, open source, security, cloud and product communities.
- top signals
- 15
- signals reviewed
- 1846
- sources tracked
- 8
-
AI & Machine LearningHugging Face Trending
all-MiniLM-L6-v2: compact sentence-embedding model for semantic search
all-MiniLM-L6-v2 is a sentence-transformers model that maps sentences and paragraphs to 384-dimensional dense vectors, suited for clustering and semantic search. It is small enough to run cheaply while keeping solid embedding quality, and ships with PyTorch, TensorFlow, ONNX, OpenVINO, and Rust implementations. Adoption is heavy: 203,243,195 downloads and 5,991 likes on Hugging Face, under an Apache-2.0 license.
Peak observed- ♥ 6.4k
- ⇣ 252M
Observed on 30 days · Hugging Face Trending
-
AI & Machine LearningHugging Face Trending
bge-m3: multilingual multi-function embedding model from BAAI
BGE-M3 is a sentence-embedding model from BAAI for sentence-similarity and feature-extraction tasks, usable with sentence-transformers. It is designed around three properties the authors call multi-functionality, multi-linguality, and multi-granularity, meaning it supports dense, sparse, and multi-vector retrieval across many languages and varying text lengths. It is MIT-licensed and ships PyTorch and ONNX weights, with 31,032,360 downloads and 3,913 likes on Hugging Face.
Peak observed- ♥ 3.9k
- ⇣ 37.3M
Observed on 30 days · Hugging Face Trending
-
AI & Machine LearningGitHub Trending
Superpowers: agentic skills framework for coding agents
Superpowers is an open-source framework and software development methodology that gives AI coding agents a set of composable skills plus initial instructions so they actually use them. Written in Shell and MIT-licensed, it covers topics like brainstorming and the software development lifecycle. The repository shows 300,155 stars and 26,806 forks, with 365 open issues.
Peak observed- ★ +973 today
- ⮂ 26.9k
Observed on 8 days · GitHub Trending
-
AI & Machine LearningGitHub Trending
skills: Matt Pocock's collection of daily agent skills
A Shell-scripted, MIT-licensed repository where TypeScript educator Matt Pocock shares the AI agent skills he uses daily for what he calls "real engineering – not vibe coding". The files come straight from his own .agents directory, so they are working examples rather than tutorials. The repo has 284,898 stars and 23,843 forks, with a homepage at aihero.dev/skills.
Peak observed- ★ +1.8k today
- ⮂ 23.8k
Observed on 9 days · GitHub Trending
-
Open Source & Dev ToolsHacker News
F-Droid 2.0
F-Droid 2.0 is a major release of the official app for the free and open-source Android app repository, delivered after more than a year of work as a complete redesign of the client and its largest overhaul to date. The announcement post notes that F-Droid says it is under threat, framing the release as a new chapter for Android freedom. It drew 1,128 points and 298 comments on Hacker News.
Peak observed- ▲ 1.1k
- 💬 298
Observed on 1 day · Hacker News, Lobste.rs
-
AI & Machine LearningGitHub Trending
ECC: performance optimization system for AI coding agents
ECC is an open-source toolkit that improves how AI coding agents such as Claude Code, Codex, Opencode, and Cursor behave, adding skills, memory, instincts, and security guardrails. Written in JavaScript and MIT-licensed, it has 278,085 stars and 41,445 forks on GitHub. The README warns users to install it only from verified channels, including the npm packages ecc-universal and ecc-agentshield.
Peak observed- ★ +1.1k today
- ⮂ 42.1k
Observed on 8 days · GitHub Trending
-
AI & Machine LearningGitHub Trending
ponytail: rules that make AI coding agents write less code
ponytail is a JavaScript repository of agent rules and skills for AI coding assistants such as Claude Code, Cursor, and other AI agents. Its guiding idea is that the best code is the code you never written, so it shapes agent behavior toward minimal, restrained solutions like a cautious senior developer would. It is MIT-licensed and has drawn 166,408 stars and 9,001 forks.
Peak observed- ★ +2.1k today
- ⮂ 9.4k
Observed on 10 days · GitHub Trending
-
Community & DiscussionHacker News
When did Google get so weird?
A blog essay by Sancho Panza recounting a recent Google search experience the author found so odd it stopped them in their tracks, prompting a broader reflection on how weird Google's behavior has become. It resonated strongly on Hacker News, drawing 1,092 points and 585 comments, indicating widespread practitioner concern about search quality and Google's shifting product behavior.
Peak observed- ▲ 1.1k
- 💬 585
Observed on 2 days · Hacker News, Lobste.rs
-
AI & Machine LearningDev.to
Dev Opportunity Radar #20: $2M AI Reasoning Challenge, PayPal AI Hackathon, and Coinbase Analytics Challenge
TL;DR Welcome back to Dev Opportunity Radar. This is a weekly series where I share opportunities,…
Peak observed- ♥ 94
- 💬 18
Observed on 2 days · Dev.to
-
AI & Machine LearningDev.to
AI Fatigue? Yea I know.
I don't know how to start this off really haha. Though to be fair, everyone is talking about AI…
Peak observed- ♥ 102
- 💬 66
Observed on 2 days · Dev.to
-
Community & DiscussionDev.to
Why you still need a Website Portfolio, even though everyone can Vibe Code it.
If you have been following me for a long time, you already know that I have been holding off on my…
Peak observed- ♥ 124
- 💬 54
Observed on 2 days · Dev.to
-
Community & DiscussionDev.to
Promise Delivered: Welcome to the DEV Hall of Fame (65 Authors, 65 Masterpieces)
Status: Promise delivered ✅ The Doors Are Open A little over a month ago, I published…
Peak observed- ♥ 169
- 💬 87
Observed on 2 days · Dev.to
-
SecuritySecurity Radar
CVE-2026-106931: EG Secure Solutions SiteGuard Server Edition OS Command Injection Vulnerability
CVE-2026-106931 is an OS command injection vulnerability affecting EG Secure Solutions SiteGuard Server Edition, a WordPress-oriented security plugin. It has been confirmed as listed in CISA's Known Exploited Vulnerabilities catalog, indicating active exploitation. Exact affected versions and mitigation steps were not available in the fetched context, so the NVD entry and vendor advisory should be consulted before acting.
Observed on 2 days · Security Radar
-
Community & DiscussionLobste.rs
oh, apparently it's not possible to portably check for string-to-float conversion errors in standard c
oh, apparently it's not possible to portably check for string-to-float conversion errors in standard c is a practitioner-focused engineering link from Lobste.rs; review it for implementation detail, operational lessons, and discussion quality.
Observed on 2 days · Lobste.rs
-
Community & DiscussionLobste.rs
Hanami, Why?: Introductions
Hanami, Why?: Introductions is a practitioner-focused engineering link from Lobste.rs; review it for implementation detail, operational lessons, and discussion quality.
Observed on 1 day · Lobste.rs
How this ranking works
Each signal is ranked within its source on each observed day, using public engagement metrics where available and the source’s ordering otherwise. Peak strength, typical strength, recurrence and discovery across sources contribute to its score. Source and topic limits keep the shortlist varied. Repeated URLs and matching titles are merged. Metrics are the highest observed snapshots; cumulative counts are never added together.
Raw daily collections preserve repeat observations that the daily digest may omit to keep its news fresh. This is a ranking of observed public signals, not site traffic or a claim of measured growth.
Daily editions behind this ranking
- 2026-10-22
- 2026-10-21
- 2026-10-20
- 2026-10-19
- 2026-10-18
- 2026-10-17
- 2026-10-16
- 2026-10-15
- 2026-10-14
- 2026-10-13
- 2026-10-12
- 2026-10-11
- 2026-10-10
- 2026-10-09
- 2026-10-08
- 2026-10-07
- 2026-10-06
- 2026-10-05
- 2026-10-04
- 2026-10-03
- 2026-10-02
- 2026-10-01
- 2026-09-30
- 2026-09-29
- 2026-09-28
- 2026-09-27
- 2026-09-26
- 2026-09-25
- 2026-09-24
- 2026-09-23