WeSearch – Anonymous news aggregator with no algorithm, 700 sources
Read a chronological, non-personalized news feed across 850+ curated publishers and an 88,000+ feed catalog. Compare sources and discuss stories anonymously — free, no paywall, no personalized ads.
WeSearch – Anonymous news aggregator with no algorithm, 700 sources launched on May 1, 2026 with 16 votes, #970 of 20,538 launches that month and more than 90% of that year's launches.
In plain words
WeSearch aggregates news from 700 sources without using algorithmic filtering, presenting stories anonymously. The platform serves readers who want diverse news coverage without algorithmic curation or personalization. What distinguishes it is its commitment to showing news from a broad range of sources while removing identifying elements, allowing users to encounter stories based on editorial selection rather than algorithmic ranking.
written from the facts on this page · September 2026
From the sources
Anonymous community news aggregator across 700+ sources. No algorithm, no paywall, no tracking — read, react, comment, share. Free, ad-free, identity-free.
One calm, chronological view across 850+ curated publishers and an 88,000+ feed catalog — with source context, market signals, and anonymous community discussion. Colin Cowherd named his top college football quarterback without hesitation, after an impressive season-opening debut. Alabama QB Keelon Russell made a bold prediction about Ryan Coleman-Williams after the team's 48-10 win over East Carolina. Georgia's blowout win over Tennessee State featured a viral moment from a breakout TE that fans say echoes Brock Bowers. German Chancellor Friedrich Merz's party faces a disastrous blow as AfD aims for Germany's first far-right state government since World War II. A hot meat pie from any…from wesearch.press
Does a similar job
all alternatives →
Real-time system that tracks how news spreads across 200k websitesNov 2025 · yandori.io · ▲256I built a system that monitors ~200,000 news RSS feeds in near real-time and clusters related articles to show how stories spread across the web. It uses Snowflake’s Arctic model for embeddings and HNSW for fast similarity search. Each “story cluster” shows who published first, how fast it propagated, and how the narrative evolved as more outlets picked it up. Would love feedback on the architecture, scaling approach, and any ways to make the clusters more accurate or useful. Live demo: https://yandori.io/news-flow/
- FTFilter the web by Hacker News2016 · hackernewsfilter.com · ▲146
A news aggregator for the Python community written in Python/Django2019 · github.com · ▲106A Hacker News lookalike written in Python/Django, powering https://news.python.sc - sebst/pythonic-news
- IBI built a tool to remove news articles from HN2020 · hn.luap.info · ▲131
Hacker News, Without AISep 2026 · unslop.news · ▲197Source: https://github.com/leiDnedyA/hn-without-ai
BloomSearch – Keyword search with hierarchical Bloom filters2025 · github.com · ▲66Hey HN! I got nerd-sniped by Bloom Filters this weekend, specifically for searching datasets with high "cardinality" (number of unique items). They're an _amazing_ data structure that, at a fixed size, tracks potential set membership. That means unlike normal b-tree indexes, they don't grow with the number of unique items in the dataset. This makes them great for "needle in a haystack" search (logs, document) as implementations like VictoriaMetrics and Bing's BitFunnel show. I've used them in the past, but they've never been center-stage in my projects. I wanted high cardinality keyword…
More growth this month
the category →
wallhop is a free paywall bypass. Paste any article link to read it without paywall popups, ads or clutter. No signup, no extension. A simple 12ft.io alternative.
Growth · 13d ago · wallhop.io
Source: Show HN post ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com