> For the complete documentation index, see [llms.txt](https://solyx.gitbook.io/solyx-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://solyx.gitbook.io/solyx-docs/readme.md). # Overview ## 2.1 What is Solyx? Solyx is a protocol that calculates AI-powered trust scores for Solana wallets based purely on onchain behavior. Instead of looking at just wallet balance, identity, or token holdings, Solyx studies how wallets act over time, how they trade, engage, and move. Using machine learning and behavioral modeling, it assigns each wallet a dynamic trust score and a set of optional behavioral tags that reflect its role in the ecosystem. The idea is simple: to give the Solana network a sense of memory and context. Solyx makes it possible to distinguish between real participants and extractive actors. It gives builders, users, and protocols the ability to filter, prioritize, and coordinate based on trust that’s earned through action, not just assumption. Each score evolves over time and reflects the credibility of the wallet behind it. In addition to automated scoring, users can also leave annotations on any wallet, adding another layer of human context. These notes are public, pseudonymous, and completely optional, giving the community a way to surface useful insights and flag patterns that models might miss. Solyx does not aim to deanonymize. It does not enforce identity, but simply offers a new layer of signal that makes decentralized coordination smarter, safer, and more meaningful. *** ## 2.2 How it works At a high level, Solyx takes in raw transaction activity and behavioral signals across the Solana network, analyzes them through scoring heuristics and machine learning models, and produces outputs like trust scores, behavior tags, and annotations. Wallets are scored continuously, with trust decaying over time if behavioral patterns stop. Tags help describe role-specific activity, for example, wallets that consistently buy and hold for a long amount of time might be tagged as "Long-Term Holder," while wallets that repeatedly snipe launches and dump quickly could be flagged as "Farmer/Sniper" Annotations let the community add real-time insight, warnings, or endorsements to any wallet. These outputs are available via dashboard, API, or oracle feeds and can be used in protocols for filtering, access control, or incentive alignment. *** ## 2.3 Core Concepts * **Trust Scores**: Quantified indicators of wallet behavior, based on heuristics, ML models, and multi-factor activity patterns. * **Behavioral Tagging**: Readable classifications such as "Long-Term Holder,", "Bundle Wallet", "Dead Wallet", or "Insider" etc. * **Wallet Clustering**: Identifying and grouping associated wallets by behavior, transaction flows, timing correlations, and proxy patterns. * **Reputation Surfaces**: UI layers, API responses, dashboards, and oracles where trust data becomes usable and actionable. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://solyx.gitbook.io/solyx-docs/readme.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.