Updated Aug 14, 2026

How X's Algorithm Actually Works

From the source code — every claim traceable to a real file in xai-org/x-algorithm.

8
Lessons
30+
Repo services
32
Weights tracked

The Lessons

Weights, Right Now

NameValue
AuthorDiversityDecay0.5
AuthorDiversityFloor0.25
BidirectionalFollowDwellWeightBoost0
BidirectionalFollowReplyWeightBoost15
BlockAuthorWeight-31.2
ClickWeight0.4
ColdStartFollowerCap1000
ColdStartImpressionThreshold1000
See all 32 weights
Try the AI Post Generator
Posts tuned to the real weights
Get API Credits
Sign up and start building

Common Questions

Is the X algorithm really open source?

Yes. xAI published the core ranking pipeline, sourcing systems, filters, and visibility logic at github.com/xai-org/x-algorithm. Some abuse-detection rules and LLM prompts are withheld to reduce gaming, but the ranking weights and pipeline structure are public.

Do the weights multiply raw engagement counts?

No. The repo explicitly warns that weights multiply the predicted probability of each action, not raw counts. A report weight of -234 does not mean one report cancels 468 likes — it scales how much the predicted likelihood of a report affects ranking.

How often does the algorithm change?

The repo is updated regularly. The bidirectional follow boost went from +20 (July 13, 2026) to +15 (July 24, 2026) after real-world feedback. Our changelog page tracks detected changes within hours of the repo updating.

X Algorithm Explained — From the Source Code | Qubax Growth Lab · Qubax AI