mrkeyoor.com_
Fri 04 Sept 01:40 UTC
AI Toolsevaluationupdated 04 Sept 2026

x-algorithm review

X Algorithm is the published core of the system that chooses and orders posts in X's For You feed. It shows how followed-account posts and recommendations from outside a user's network are retrieved, scored, filtered, and blended with items such as ads and follow suggestions. Its main value is transparency and study, rather than providing a ready-made social feed you can deploy unchanged.

trackingstars / 7d
Verdict

Our measured slice installed in 42 seconds, built in 5 seconds, and completed its pytest run in 7 seconds with 32 passed and 0 failed. Use this repository as unusually concrete primary material for understanding X's feed, especially the boundary between ranking and visibility enforcement. Do not treat that successful component run as evidence that the whole service is a packaged product: the missing releases, CI workflows, Dockerfile, production data, and infrastructure make adoption a serious engineering project.

We ran it

Install✓ · 42s62 packages · 354 MB
Build✓ · 5s
Tests✓ · 7s32 passed · 0 failed · 3 skipped of 32 (pytest)
Known vulns0(pip-audit)
Repo2045 files~288,391 lines of source · 14 MB · 0 CI workflows · tests dir

Answers from our run

Does x-algorithm build from source?

Dependencies installed in 42 seconds (62 packages), and the build succeeded in 5 seconds. We cloned commit e4dcedd into a clean Debian container with 3 CPUs and no project-specific setup.

Do x-algorithm's tests pass?

Yes: 32 of 32 passed when we ran the project's own test command (pytest). Some failures need services or credentials a bare container does not have.

Does x-algorithm have known vulnerabilities in its dependencies?

pip-audit found none in the dependency tree at the time of our run.

Who should not use x-algorithm?

Teams expecting a one-command, complete X clone, because important production infrastructure and data are absent

What are the alternatives to x-algorithm?

The Algorithm, RecBole, Microsoft Recommenders. Our measured slice installed in 42 seconds, built in 5 seconds, and completed its pytest run in 7 seconds with 32 passed and 0 failed.

Setup3/5Measured Python component worked; the whole stack is not packaged
Docs4/5Clear architecture and component links, with deployment gaps
Community4/532,581 stars and a push yesterday, but 87 open issues
Maturity3/5Production-derived code without a versioned standalone release

Who it’s for

Recommendation engineers studying a large, real-world feed design
Researchers auditing how ranking, labels, and visibility rules interact
Platform teams looking for concrete retrieval, scoring, and filtering patterns
Developers willing to extract and adapt individual components

Who it’s NOT for

Teams expecting a one-command, complete X clone, because important production infrastructure and data are absent
Small apps that only need a conventional chronological feed
Operators who need versioned releases, container images, or documented deployment support
Anyone seeking a neutral reference architecture without platform-specific policy choices

Setup reality

Our run succeeded, but only for the Python project under ./bdsm/: installation took 42 seconds for 62 packages and used 354 MB, the build took 5 seconds, and tests took 7 seconds, with pytest reporting 32 passed, 0 failed, and 3 skipped of 32. That is encouraging for the measured component, not proof that the entire 2,045-file, mostly Rust feed system is turnkey. The repository has tests but no CI workflow files and no Dockerfile, so reproducing the full stack will require more assembly than the architectural README initially suggests.

This is a transparency release before it is a product

X Algorithm publishes the core logic behind the For You feed, where the useful question is not merely which posts are popular, but which posts should be eligible and useful for one viewer. The repository separates candidate discovery, ranking, and visibility decisions clearly enough to make a complicated feed understandable. It is most useful for study, since reuse assumes X's surrounding services and data.

The request path starts with query hydration, including recent engagements, follows, blocks, mutes, muted keywords, and already served posts. Candidate retrieval then combines 2 broad pools: Thunder supplies recent in-network posts, while Phoenix retrieval and SimClusters find out-of-network material. A common model ranks those candidates, after which the blending pipeline adds material outside model ranking, including ads, prompts, and Who to Follow suggestions. The August 13, 2026 update also published Phoenix training code and synthetic-data generation for a proof-of-concept run.

What happened when we ran it

Our run covered the Python project in ./bdsm/, not every service in this large repository. Installation succeeded in 42 seconds, adding 62 packages and consuming 354 MB on disk. The build then succeeded in 5 seconds. Tests completed in 7 seconds, with pytest reporting 32 passed, 0 failed, and 3 skipped of 32. Pip-audit found 0 known vulnerabilities. These results came from commit e4dcedd in a fresh, unprivileged Debian container with 3 CPUs, 8 GB of RAM, no secrets, and a Python 3.12 uv image.

It does not establish performance, model quality, or end-to-end feed behavior. We measured a repository containing 2,045 files, about 288,391 lines of source, and a 14 MB checkout, yet the runnable target was one subproject. There were 0 CI workflow files and no Dockerfile, although a tests directory exists. Anyone assessing adoption should regard the lab result as a component-level reproducibility check, not a production deployment rehearsal.

The architecture explains decisions instead of hiding them

The strongest design choice is the explicit separation of ranking from eligibility. Phoenix predicts a viewer's likelihood of taking actions on a post, and code-held weights combine those predictions into a score. Visibility filtering separately decides whether content can appear, be dropped, or sit behind an interstitial. That distinction matters because a highly ranked candidate can still be ineligible due to viewer actions or labels. The repository names the systems feeding those labels, including BotMaker rules, Scarecrow, Agatha, media analysis components, user credibility scoring, and abuse enforcement.

The documentation also corrects an easy but consequential misunderstanding. As clarified on August 14, 2026, an action weight scales a predicted probability for that viewer, not the raw count of likes, shares, reports, or other actions. Therefore, comparing two weight values does not tell you that one observed report cancels a fixed number of observed likes. Comments were added to the parameter and ranking-scorer code to reduce that misreading.

The Brazil election filter shows the other side of that transparency. It removes posts from accounts reported to Brazil's Electoral Court for the 2026 election unless the viewer follows the account, and the README says its account list was updated on August 27, 2026. Whether you agree with the policy or not, the code exposes that such a rule exists and where it acts. The Under the Hood tool is presented as a related way for people to inspect aggregate label statistics that may limit the visibility of their accounts and posts.

Missing infrastructure limits direct reuse

The repository itself says that some things are not included, and the published code plainly depends on context beyond source files. A useful feed requires live behavioral data, candidate stores, labeling pipelines, policy inputs, trained artifacts, and service operations. Synthetic Phoenix data can support a proof of concept, but it cannot reproduce the distribution or feedback loops of X traffic. The absence of a tagged release also leaves adopters without a stable version boundary, upgrade notes, or a packaged artifact they can pin with confidence.

Operational polish is the clearest rough edge. With 0 GitHub Actions workflow files and no Dockerfile in our inspection, the repository does not provide an obvious automated path from checkout to consistently verified full-system build. The successful ./bdsm/ test run helps, but Rust is the repository's listed primary language and our measurement does not cover every Rust service. Documentation is detailed about request flow and policy components, yet a platform team still has to determine which pieces are independently runnable and which are coupled to internal equivalents.

Active code matters more than the absent release list

Project health looks strong on activity and attention, but mixed on supportability. The repository had 32,581 stars, 87 open issues, and a last push on September 3, 2026, one day before this review. GitHub Trending also recorded 37 stars that day. Those signals show current interest and recent work. They do not tell us how quickly maintainers answer issues, and the lack of listed releases means there is no visible cadence of stable checkpoints. It would be wrong to call the project abandoned, but equally wrong to equate popularity with a supported developer product.

It belongs beside your recommender, not at the center of deployment

In a real stack, this repository fits best as a reference and source of patterns. Teams can study its parallel candidate sources, shared ranking stage, separate visibility gate, and configuration-driven action scoring while keeping their own data contracts and policy layer. Individual components may also inform experiments, provided engineers isolate dependencies and validate behavior against local requirements. For a fresh recommendation service, RecBole or Microsoft Recommenders offers a more adaptable starting point; for historical comparison, twitter/the-algorithm is the direct counterpart. Choose X Algorithm when fidelity to X's published design is the point, not when the goal is the shortest route to shipping a feed.

Alternatives

ProjectWhat it isPick it when
The AlgorithmThe earlier public snapshot of Twitter's recommendation code and supporting services.Pick this instead when you need to compare the current design with the older Twitter-era implementation.
RecBoleA research-focused recommendation library with reusable models and evaluation tooling.Pick this instead when you want to train and compare recommenders on your own dataset rather than inspect one platform's architecture.
Microsoft RecommendersExamples and utilities for building, evaluating, and operating recommendation systems.Pick this instead when practical notebooks and adaptable implementation patterns matter more than X-specific ranking transparency.

What people are saying

  1. [github-trending] xai-org/x-algorithm

Sources

  1. xai-org/x-algorithm on GitHub

More ai tools reviews

InvokeAI · deep-swe · go-micro · learnopencv · vit-pytorch · Scrapegraph-ai · the whole board →