Sauver: An open-source, local AI agent that fights email slop

Hacker News AI Topby mszczodrakMarch 31, 20261 min read0 views

Article URL: https://sauver.org Comments URL: https://news.ycombinator.com/item?id=47592285 Points: 1 # Comments: 0

[ THE RESISTANCE IS ACTIVE ]

KEEP AI SLOP OUT OF YOUR INBOX.LET THE SPAMMERS WASTE THEIR TIME.

AI made it effortless to flood your inbox with slop. We made it effortless to fight back. Stop the slop. Watch the spammers scream into the abyss. Join the anti-AI-slop resistance.

Local-first · Private · MIT Licensed

█

THE MANIFESTO

YOUR INBOX IS ASURVEILLANCE STATE.

AI was supposed to make us 10x more productive. Instead, the attention merchants, including lead generators, growth hackers, and their armies of automated outreach tools, have weaponized it to build a slop-machine that bombards your inbox and taxes your sanity. They've turned your most private tool, your email, into surveillance infrastructure for automated predators who see your time as raw material.

It is not your fault. No human was ever meant to compete with a thousand bots.

The attention merchants, including lead generators, growth hackers, and their armies of automated tools, were handed AI and used it to build a slop-machine that bombards your inbox and taxes your sanity.

No human was ever meant to compete with a thousand bots firing at them simultaneously. The system isn't broken. It's working exactly as they intended.

We confirm what you've always suspected: that "personalized" pitch was written by a machine, and that hidden pixel is watching you. We make your defense active.

None of us are fighting alone. Every trap deployed, every pixel stripped, and every bouncer reply sent by any of us drains their resources. Our collective resistance is a DDoS against the attention economy.

People like us don't accept the default. We fight back. Together we overwhelm them.

Welcome to the resistance.

Privacy-Conscious Users

Stop hidden tracking pixels from reporting your activity back to senders.

The Fighter

You don't just want slop filtered. You want the senders to feel it. You believe passive filtering is letting them win.

Deep Workers

Reclaim your attention from the bombardment of low-quality, automated outreach.

Tracker Shielding

Identifies and neutralizes 1×1 tracking pixels and surveillance beacons before they phone home.

Slop Detection

AI classification distinguishes genuine human outreach from machine-generated "job slop" and sales templates.

Expert-Domain Traps

Fires hyper-specific, technically demanding questions at recruiters to shift the cognitive load back to the sender.

Bouncer Replies

Engages generic spammers with absurd, bureaucratic, or confusing automated replies to waste their resources.

Inbox Triage

Categorizes, labels, and archives emails by content and risk level, keeping your focus on what matters.

NDA Trap

When a sender repeats the same pitch 3 or more times, Sauver sends them an NDA to sign before any further communication.

Bot Detection

Detects near-instant replies across consecutive exchanges, silently archiving bot-driven threads.

THE BOUNCER REPLY

DON'T JUST FILTER.FIGHT BACK.

When Sauver detects a recruiter mass-blast or sales template, it doesn't just archive it. It deploys an Expert Domain Trap, a hyper-specific technical challenge no automated system can answer. The cognitive load shifts permanently back to the sender.

⟹

Expert Domain Traps

Hyper-specific questions only a real human can answer, customized to the sender's claimed domain.

⊘

Bouncer Replies

Engages generic spammers with absurd, bureaucratic, or confusing automated replies to drain their resources.

Trackers Blocked

0.0%

Detection Accuracy

Time Reclaimed

0.0%

Slop Reduction

The installer handles everything — backend deployment, AI client configuration, and slash commands. Requires Node.js v18+.

curl -fsSL https://sauver.org/install.sh | bash

Once installed, open Claude Code or Gemini CLI and run:

/sauver

No OAuth setup, no API keys, no manual configuration. See the full setup guide →

[ SECURE COMMS CHANNEL ]

THE BOTS WILL ADAPT.SO WILL WE.

AI spammers are constantly changing their tactics. Drop your email below, and we'll ping you only when there are major core updates or new filters added to the repository.

Type /sauver in Claude Code or Gemini CLI. Sauver scans your inbox, strips trackers, classifies each email, and drafts counter-measures — all in one shot.

█

Original source

Hacker News AI Top

https://sauver.org

Was this article helpful?

Ask AI about this article

Ready

Conversation starters

Ask anything about this article…

Daily AI Digest

Get the top 5 AI stories delivered to your inbox every morning.

More about

open-sourceagent

ProductsLive

Web Scraping Is Dead. Web Agents Just Replaced It.

Last month, I needed to pull together a competitive landscape report. Nothing exotic — pricing trends, feature comparisons, market positioning across about 30 to 40 industry sites and competitor pages. Sounds manageable, right? Here's what actually happened. Half the sites loaded data dynamically — you scroll down, content appears, but view-source shows empty divs. A few required creating accounts just to see pricing. Others buried the good stuff behind three layers of filters and dropdown menus. And two sites hit me with CAPTCHAs the moment I tried to load them in an automated way. I did what I always do: opened 40 Chrome tabs, spent two days copying and pasting into a spreadsheet, and ended up with a document that was already going stale by the time I finished for

DEV Community

11m20 minutes ago

ReleasesLive

Monitor Insider Trading Without Parsing SEC XML — Form 4 Data as Clean JSON

<h1> Monitor Insider Trading Without Parsing SEC XML — Form 4 Data as Clean JSON </h1> SEC Form 4 filings are one of the most useful public datasets for tracking what company insiders (CEOs, directors, 10% owners) are doing with their stock. When a CEO buys 50,000 shares of their own company, that's a signal. The problem: getting this data from SEC EDGAR is genuinely painful. <h2> The EDGAR Problem </h2> EDGAR serves filings as nested XML/SGML documents. There's no proper REST API for structured Form 4 data. Here's what you're dealing with: <ol> <li> CIK-based lookups: You need to map ticker symbols to CIK numbers (EDGAR's internal ID system)</li> <li> Full-text search returns everything: Searching for "AAPL" returns all 100+ filing ty

DEV Community

7m19 minutes ago

Open Source AILive

I Built a Social Post Engine to Escape the Canva-Export-Schedule Loop

As a solo founder running WahResume.com, I was spending way too much time on social media - not on creativity, but on process. Same templates. Same brand assets. Same hashtags. Every post meant opening Canva, exporting, uploading, scheduling… and repeating it the next day. So I built something to fix that. Social Post Engine is a small tool that helps me stay consistent on social media without having to touch Canva or an endless queue of schedulers. Here’s what it does: ✅ Seed & review topics in one command — it researches, outlines, and preps your next posts. ✅ Pre-generates branded images from templates (checklists, stat cards, charts, comparisons). It also writes captions in your brand’s voice using AI. ✅ Publishes automatically to LinkedIn

DEV Community

2m11 minutes ago

Knowledge Map

TopicsEntitiesSource

Connected Articles — Knowledge Graph

This article is connected to other articles through shared AI topics and tags.

Knowledge Graph100 articles · 190 connections

Scroll to zoom · drag to pan · click to open

Discussion

No comments yet — be the first to share your thoughts!

More in Releases

ReleasesLive

VisiPrint system generates realistic 3D-print previews from two images

Designers, makers, and others often use 3D printing to rapidly prototype a range of functional objects, from movie props to medical devices. Accurate print previews are essential so users know a fabricated object will perform as expected. But previews generated by most 3D-printing software focus on function rather than aesthetics. A printed object may end up with a different color, texture, or shading than the user expected, resulting in multiple reprints that waste time, effort, and material.

Phys.org AI

1m21 minutes ago

ReleasesLive

Monitor Insider Trading Without Parsing SEC XML — Form 4 Data as Clean JSON

DEV Community

7m19 minutes ago

ReleasesLive

The Inversion Error: Why Safe AGI Requires an Enactive Floor and State-Space Reversibility

A systems design diagnosis of hallucination, corrigibility, and the structural gap that scaling cannot close The post The Inversion Error: Why Safe AGI Requires an Enactive Floor and State-Space Reversibility appeared first on Towards Data Science .

Towards Data Science

1mabout 1 hour ago

ReleasesLive

Why We Built an API for Spanish Fiscal ID Validation Instead of Just Implementing It

A few months ago I was integrating fiscal identifier validation into a project. I googled it, found a 30-line JavaScript function, copied it, tested it with four cases, and it worked. I dropped it into the codebase and forgot about it. Three months later, a user emailed us: their CIF wasn't validating. It was a perfectly valid CIF. That's when I understood there's a difference between implementing validation and maintaining it correctly. <h2> The problem isn't that it's hard </h2> Validating a NIF seems straightforward: 8 digits, one letter, modulo 23. Any developer can implement it in ten minutes. The problems appear when you scratch the surface: NIF: the basic algorithm works, but there are special f

DEV Community

5mabout 1 hour ago