The algorithm isn't a secret.
It's on GitHub.
Bangermeter scores every post in your X feed with the formula X open-sourced. Real published weights, every factor cited to its source. No folklore numbers, no data collection, no server.
Add to Chrome · Free Read the codeSee it on your feed
The live UI: badges in the feed, breakdown on click. Same screenshot as the Chrome Web Store listing.
What you get
A score badge on every tweet
As you scroll x.com, each post gets a badge with up to two 0 to 100 scores (50 = a typical median post). C is Content Appeal: what the algorithm would predict from the content alone. E is Earned Engagement: how its weights value what the post actually earned per view. A ~ marks low-view posts where rates are statistically smoothed.
Click for the plain-English breakdown
Big score chips, human explanations ("12 replies, the algorithm's favorite, each worth ~27 likes"), detected content signals with ▲/▼ direction, rescoring factors, freshness decay, and a collapsible "Show the math" with the full weight × probability table.
A live draft meter while you write
The compose box gets a meter that scores your draft in real time with ▲/▼ hints: asks a question ▲, three or more hashtags ▼, "like if" bait ▼.
Sourced signals X never weighted publicly
Shares ("DM-forwarding is one of the strongest signals," Musk, Sept 2024), bookmark as a "quiet like," dwell thresholds (a click only counts after 2 seconds), and Grok's "banger screen" quality gate. Each with its provenance, none with an invented number.
Special detections
Community-Noted posts (score suppressed ×0.5, per three causal studies), visibility-limited posts flagged qualitatively, and quote-tweets handled correctly: embedded media is not counted as the quoting post's own.
Settings that stay yours
Toggle badges, the draft meter, out-of-network mode (×0.75), and an optional 2023 "verified boost" historical mode, off by default. Settings sync through Chrome's own storage. That is the only permission it wants.
How it works
- The engine is a faithful port of the exact scoring formula from X's open-sourced the-algorithm repo: a weighted sum of engagement probabilities, multiplied by rescoring factors. The same formula skeleton survives in X's 2026 open-source release (xai-org/x-algorithm), though X now redacts the weight values there.
- The weights are the April 5, 2023 snapshot: the last weight values X published. X's own README admits weights are "periodically adjusted," so Bangermeter frames every output as a relative score against a typical post. It does not predict reach.
- Heads X never published values for (bookmarks, shares, dwell) stay out of the score entirely. They show up as sourced signals instead.
- Observed engagement rates get empirical-Bayes shrinkage, so a post with 1 reply in 19 views can't fake a viral score.
- Everything runs locally in your browser: zero network requests, no analytics, no account. MIT licensed, open source, 33 self-tests, X-DOM test suite in the repo.
We read the code so you don't have to trust screenshots
Bangermeter sits on three multi-agent research sweeps (roughly 2M tokens of source-traced investigation, Aug 2026), all documented in the repo's RESEARCH.md:
- Validation pass. Confirmed the April 2023 weight table is the last sourced set X released, and that the weighted-sum skeleton survives in X's 2026 open-source release (xai-org/x-algorithm).
- The folklore hunt. Every viral "leaked weight" was traced to its origin and debunked: "bookmark = 20× a like," "a link costs you 30 to 50 percent," "3+ hashtags = minus 40 percent," "block is minus 120, mute is minus 100" (that one traces to an unaffiliated fan site's invented numbers). None survives source-tracing.
- The leak hunt. Swept court records, EU DSA proceedings, patents, scrubbed git history, and ex-employee disclosures. Found: the two-snapshot weight history, the archived 2023 verified-author multipliers (×4/×2, later removed from X's code), a granted Twitter patent with a fitted engagement-vs-followers power law, and the fully open Community Notes algorithm with three causal studies quantifying a noted post's engagement suppression.
And the punchline: those viral Grok "algorithm reveal" screenshots are confabulations by construction. The weights are redacted from everything Grok can read.
Receipts
Who it's for
Creators and marketers
Who want to understand why posts perform instead of chasing folklore.
The algorithm-curious
Who will open "Show the math" and check the weight table themselves.
Anyone tired of the threads
The "I reverse-engineered the algorithm" ones with made-up numbers.
Get it
Tampermonkey userscript
Same tool, single file, for people who don't install extensions: extension/bangermeter.user.js in the repo.
Load it yourself
Clone the repo, open chrome://extensions, enable Developer mode, Load unpacked, pick the extension/ folder. Read the code before you run it. That's the point of it being open.
FAQ
Does it predict how many views I'll get?
Is this the current algorithm?
What data do you collect?
Why do some huge accounts outperform their scores?
Is it free?
Bangermeter is an independent open-source project. Not affiliated with, endorsed by, or sponsored by X Corp or xAI. Scores are relative estimates derived from X's published open-source code and cited public research; they are not predictions of reach.
Built by Ryan Lenk. More projects on the Side Projects page.